< Prev | Home | Model | Random | Next >

Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')



Text #0

Max Range: 4.4029. Min Range: -4.4029

Max Act: 4.4029. Min Act: -0.0000

Data Index: 1621849 (Python Code)

Max Activating Token Index: 100

Click toggle to see full text

Truncated

"""   

 self.path = path  
 """  
 *path* (:class:`str`) is the path of the entry.  
 """   

 self._stat = stat  
 """  
 *_stat* (:class:`~os.stat_result`) is the stat result

Full Text #0

<|BOS|>.stat_result`) is the stat result of the direct  
 entry.  
 """   

 self.name = name  
 """  
 *name* (:class:`str`) is the base name of the entry.  
 """   

 self.path = path  
 """  
 *path* (:class:`str`) is the path of the entry.  
 """   

 self._stat = stat  
 """  
 *_stat* (:class:`~os.stat_result`) is the stat result of the linked  
 entry.  
 """  

 def is_dir(self, follow_links=None):  
 # type: (Optional[bool]) -> bool  
 """  
 Get whether the entry is a directory.   

 *follow_links* (:class:`bool` or :data:`None`) is whether to follow  
 symbolic links. If this is :data:`True`, a symlink to a directory  
 will result in :data:`True`. Default is :data:`None` for :data:`True`.   

 Returns whether the entry is a directory (:class:`bool`).  
 """  
 if follow_links is None:   
 follow_links = True   

 node_stat = self._stat if follow_links else self._lstat  
 return stat.S_ISDIR(node_stat.st_mode)  

 def is_file(self, follow_links=None):  
 # type: (Optional[bool]) -> bool  
 """  
 Get whether the entry is a regular file.   

 *follow_links* (:class:`bool` or :data:`None`) is whether to follow  
 symbolic links. If this is :data:`True`, a symlink to a regular file  
 will result in :data:`True`. Default is :data:`None` for :data:`True`.   

 Returns whether the entry is a regular file (:class:`bool`).  
 """  
 if follow_links is None:   
 follow_links = True   

 node_stat = self._stat if follow_links else self._lstat  
 return stat.S_ISREG(node_stat.st_mode)  

 def is_symlink(self):  
 # type: () -> bool  
 """  
 Returns whether the entry is a symbolic link (:class:`bool`).  
 """  
 return stat.S_ISLNK(self._lstat.st_mode)  

 def stat(self, follow_links=None):  
 # type: (Optional[bool]) -> os.stat_result  
 """  
 Get the cached stat result for the entry.   

 *follow_links* (:class:`bool` or :data:`None`) is whether to follow  
 symbolic links. If this is :data:`True`, the stat result of the  
 linked file will be returned. Default is :data:`None` for :data:`True`.   

 Returns that stat result (:class:`~os.stat_result`).  
 """  
 if follow_links is None:   
 follow_links = True   

 return self._stat if follow_links else self._lstat 
<|EOS|>import codecs 
import fnmatch 
import os 
import sublime 
import sublime_plugin 
import time 
import re 
 
try:  # Python 3    
 from .haxe_helper import HaxeComplete_inst, get_classpaths    
 from .haxe_generate_code_helper import is_haxe_scope, get_context    
 from .haxe_organize_imports import HaxeOrganizeImports    
 from .haxe_parse_helper import * 
except (ValueError):  # Python 2    
 from haxe_helper import HaxeComplete_inst, get_classpaths    
 from haxe_generate_code_helper import is_haxe_scope, get_context    
 from haxe_organize_imports import HaxeOrganizeImports    
 from haxe_parse_helper import * 
 
from xml.etree import ElementTree 
 
try:    
 from elementtree import SimpleXMLTreeBuilder    
 ElementTree.XMLTreeBuilder = SimpleXMLTreeBuilder.TreeBuilder 
except ImportError as e:    
 pass  # ST3 
 
result_file_regex = (    
 r'^(.+):(\d+)'    
 r'(?:: (?:lines \d+-\d+|character(?:s \d+-| )(\d+)) : )?'    
 r'(?:(?!Defined in this class).)*$') 
re_haxe_position = re.compile(    
 r'^(.+):(\d+): (?:

Text #1

Max Range: 4.4029. Min Range: -4.4029

Max Act: 3.2769. Min Act: -0.0000

Data Index: 1418144 (Python Code)

Max Activating Token Index: 52

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 4.4029. Min Range: -4.4029

Max Act: 2.9456. Min Act: -0.0000

Data Index: 1463032 (Python Code)

Max Activating Token Index: 989

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 4.4029. Min Range: -4.4029

Max Act: 3.0323. Min Act: -0.0000

Data Index: 1650578 (Python Code)

Max Activating Token Index: 246

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 4.4029. Min Range: -4.4029

Max Act: 3.0396. Min Act: -0.0000

Data Index: 1388868 (Python Code)

Max Activating Token Index: 47

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 4.4029. Min Range: -4.4029

Max Act: 2.9540. Min Act: -0.0000

Data Index: 1418361 (Python Code)

Max Activating Token Index: 638

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 4.4029. Min Range: -4.4029

Max Act: 2.9052. Min Act: -0.0000

Data Index: 1475909 (Python Code)

Max Activating Token Index: 142

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 4.4029. Min Range: -4.4029

Max Act: 2.8265. Min Act: -0.0000

Data Index: 1432005 (Python Code)

Max Activating Token Index: 448

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 4.4029. Min Range: -4.4029

Max Act: 2.6498. Min Act: -0.0000

Data Index: 1597819 (Python Code)

Max Activating Token Index: 633

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 4.4029. Min Range: -4.4029

Max Act: 2.8497. Min Act: -0.0000

Data Index: 1618226 (Python Code)

Max Activating Token Index: 820

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 4.4029. Min Range: -4.4029

Max Act: 2.5577. Min Act: -0.0000

Data Index: 1549118 (Python Code)

Max Activating Token Index: 382

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 4.4029. Min Range: -4.4029

Max Act: 2.4132. Min Act: -0.0000

Data Index: 1591505 (Python Code)

Max Activating Token Index: 373

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 4.4029. Min Range: -4.4029

Max Act: 2.5106. Min Act: -0.0000

Data Index: 1523053 (Python Code)

Max Activating Token Index: 18

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 4.4029. Min Range: -4.4029

Max Act: 2.5956. Min Act: -0.0000

Data Index: 1584317 (Python Code)

Max Activating Token Index: 194

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 4.4029. Min Range: -4.4029

Max Act: 2.3067. Min Act: -0.0000

Data Index: 1496266 (Python Code)

Max Activating Token Index: 792

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 4.4029. Min Range: -4.4029

Max Act: 2.5591. Min Act: -0.0000

Data Index: 1550749 (Python Code)

Max Activating Token Index: 72

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 4.4029. Min Range: -4.4029

Max Act: 2.6877. Min Act: -0.0000

Data Index: 1459326 (Python Code)

Max Activating Token Index: 289

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 4.4029. Min Range: -4.4029

Max Act: 2.4463. Min Act: -0.0000

Data Index: 1416939 (Python Code)

Max Activating Token Index: 788

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 4.4029. Min Range: -4.4029

Max Act: 2.3294. Min Act: -0.0000

Data Index: 1431503 (Python Code)

Max Activating Token Index: 120

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 4.4029. Min Range: -4.4029

Max Act: 2.3046. Min Act: -0.0000

Data Index: 1644374 (Python Code)

Max Activating Token Index: 454

Click toggle to see full text

Truncated

Full Text #19