< Prev | Home | Model | Random | Next >

Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 2043 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')



Text #0

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0608. Min Act: -0.0002

Data Index: 1486747 (Python Code)

Max Activating Token Index: 162

Click toggle to see full text

Truncated

 by this rule.                
 # You can access the value of the current node's attribute value by: attr_value.                
 # You can access any attribute x of this node by: this['x'].                
 # If the constraint relies on attribute values from other nodes,                
 # use the LHS/

Full Text #0

<|BOS|> attribute value by: attr_value.                
 # You can access any attribute x of this node by: this['x'].                
 # If the constraint relies on attribute values from other nodes,                
 # use the LHS/NAC constraint instead.                
 # The given constraint must evaluate to a boolean expression.                
 #===============================================================================                 

 return attr_value == "entities"          


 def eval_attr15(self, attr_value, this):         
                
 #===============================================================================                
 # This code is executed when evaluating if a node shall be matched by this rule.                
 # You can access the value of the current node's attribute value by: attr_value.                
 # You can access any attribute x of this node by: this['x'].                
 # If the constraint relies on attribute values from other nodes,                
 # use the LHS/NAC constraint instead.                
 # The given constraint must evaluate to a boolean expression.                
 #===============================================================================                 

 return attr_value == "features"  

                 

 def constraint(self, PreNode, graph):                
 """                
 Executable constraint code.                
 @param PreNode: Function taking an integer as parameter                                
 and returns the node corresponding to that label.                
 """                
 #===============================================================================                
 # This code is executed after the nodes in the LHS have been matched.                
 # You can access a matched node labelled n by: PreNode('n').                
 # To access attribute x of node n, use: PreNode('n')['x'].                
 # The given constraint must evaluate to a boolean expression:                
 #    returning True enables the rule to be applied,                
 #    returning False forbids the rule from being applied.                
 #===============================================================================                 

 return True         
 
<|EOS|># Copyright (c) 2013, Web Notes Technologies Pvt. Ltd. and Contributors 
# MIT License. See license.txt 
 
# For license information, please see license.txt 
 
from __future__ import unicode_literals 
from webnotes.model.doc import Document, make_autoname 
 
import webnotes 
 
class DocType: 
 def __init__(self, d, dl):  
 self.doc, self.doclist = d, dl  

 def validate(self):  
 self.get_equipmentid_record()  

 def get_equipmentid_record(self):  
 #webnotes.errprint(self.doc.equipment_id)  
 eid=webnotes.conn.sql("select name from `tabTransformer` where equipment_id='"+self.doc.equipment_id+"'",as_list=1)  
 if eid:   
 webnotes.msgprint("Equipment ID which you select is aleready assign in Transformer Entry='"+eid[0][0]+"'",raise_exception=1)  
 else:   
 pass   


 def get_new_equipmentid(self,args):  
 dic=eval(args)  
 d = Document("Reporting Person History")  
 d.ad_type='Transformer'  
 d.plant=(dic['plant'])  
 d.client = (dic['client'])  
 d.sub_station= (dic['sub station'])  
 d.functional_location=(dic['functional_location'])  
 d.equipment_id=(dic['equipment_id'])  
 d.save()  
 return{  
 "equipment_id":'',  
 "sample_no":'',  
 "make":'',  
 "rating":'',  
 "ratio":'',  
 "phase":'',  
 "year_of_mfg":'',  
 "serial_no":'',  
 "voltage_ratio":''  
 }<|EOS|>#!/usr/bin/python 
#-*-coding: utf-8 -*- 
 
from decimal import * 
getcontext().prec = 8 
 
# Insert a new square into the HTML file with the specified parameters: 
def makeNewSquare(edge_size, offset_left, offset_top, color): 
 new_square_string = "\t\t\t\t<i style=\"position:absolute;display:inline-block;width: %sem;height: %sem;border:none;left: %sem;top: %sem;background-color: %s \"></i>\n" % (edge_size, edge_size, offset_left, offset_top, color) 
 output_file.write(new_square_string)  

 
# How long the shortest edge will be (for now in ems) 
spiral_size_short_edge = Decimal('30') 
# The smallest square is guaranteed to be larger than this: 
short

Text #1

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0674. Min Act: -0.0002

Data Index: 1532373 (Python Code)

Max Activating Token Index: 578

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0576. Min Act: -0.0002

Data Index: 1398025 (Python Code)

Max Activating Token Index: 701

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0592. Min Act: -0.0002

Data Index: 1614080 (Python Code)

Max Activating Token Index: 237

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0527. Min Act: -0.0001

Data Index: 816541 (C4 (Web Text))

Max Activating Token Index: 805

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0542. Min Act: -0.0002

Data Index: 1507625 (Python Code)

Max Activating Token Index: 421

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0540. Min Act: -0.0002

Data Index: 1549150 (Python Code)

Max Activating Token Index: 664

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0519. Min Act: -0.0002

Data Index: 834295 (C4 (Web Text))

Max Activating Token Index: 1017

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0517. Min Act: -0.0002

Data Index: 1599152 (Python Code)

Max Activating Token Index: 781

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0541. Min Act: -0.0002

Data Index: 1364386 (Python Code)

Max Activating Token Index: 239

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0519. Min Act: -0.0002

Data Index: 1652917 (Python Code)

Max Activating Token Index: 879

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0513. Min Act: -0.0002

Data Index: 1525392 (Python Code)

Max Activating Token Index: 255

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0508. Min Act: -0.0002

Data Index: 1416009 (Python Code)

Max Activating Token Index: 642

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0507. Min Act: -0.0002

Data Index: 944355 (C4 (Web Text))

Max Activating Token Index: 462

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0505. Min Act: -0.0002

Data Index: 806858 (C4 (Web Text))

Max Activating Token Index: 304

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0521. Min Act: -0.0002

Data Index: 1399485 (Python Code)

Max Activating Token Index: 153

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0481. Min Act: -0.0002

Data Index: 1583982 (Python Code)

Max Activating Token Index: 626

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0517. Min Act: -0.0002

Data Index: 1376115 (Python Code)

Max Activating Token Index: 873

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0535. Min Act: -0.0002

Data Index: 1413887 (Python Code)

Max Activating Token Index: 641

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 0.0674. Min Range: -0.0674

Max Act: 0.0524. Min Act: -0.0002

Data Index: 237367 (C4 (Web Text))

Max Activating Token Index: 514

Click toggle to see full text

Truncated

Full Text #19