Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer

Dataset: Open Web Text

Neuron 442 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gpt2-small')

Click the toggle to see the full text!

Text #0

Max Range: 2.6029. Min Range: -2.6029

Max Act: 2.6020. Min Act: -0.1277

Data Index: 1142354 (Open Web Text)

Max Activating Token Index: 1022

Text #1

Max Range: 2.6029. Min Range: -2.6029

Max Act: 2.6029. Min Act: -0.1215

Data Index: 6646722 (Open Web Text)

Max Activating Token Index: 1017

Text #2

Max Range: 2.6029. Min Range: -2.6029

Max Act: 2.5698. Min Act: -0.1029

Data Index: 3442451 (Open Web Text)

Max Activating Token Index: 1011

Text #3

Max Range: 2.6029. Min Range: -2.6029

Max Act: 2.5586. Min Act: -0.1267

Data Index: 5151833 (Open Web Text)

Max Activating Token Index: 1008

Text #4

Max Range: 2.6029. Min Range: -2.6029

Max Act: 2.5639. Min Act: -0.1042

Data Index: 4502639 (Open Web Text)

Max Activating Token Index: 1021

Text #5

Max Range: 2.6029. Min Range: -2.6029

Max Act: 2.5577. Min Act: -0.1192

Data Index: 2997911 (Open Web Text)

Max Activating Token Index: 1019

Text #6

Max Range: 2.6029. Min Range: -2.6029

Max Act: 2.5441. Min Act: -0.1700

Data Index: 8114774 (Open Web Text)

Max Activating Token Index: 1021

Text #7

Max Range: 2.6029. Min Range: -2.6029

Max Act: 2.5438. Min Act: -0.1438

Data Index: 1891122 (Open Web Text)

Max Activating Token Index: 1021

Text #8

Max Range: 2.6029. Min Range: -2.6029

Max Act: 2.5582. Min Act: -0.1359

Data Index: 7517174 (Open Web Text)

Max Activating Token Index: 1019

Text #9

Max Range: 2.6029. Min Range: -2.6029

Max Act: 2.5492. Min Act: -0.1159

Data Index: 30751 (Open Web Text)

Max Activating Token Index: 1008

Text #10

Max Range: 2.6029. Min Range: -2.6029

Max Act: 2.5627. Min Act: -0.1285

Data Index: 4294658 (Open Web Text)

Max Activating Token Index: 1021

Text #11

Max Range: 2.6029. Min Range: -2.6029

Max Act: 2.5474. Min Act: -0.1551

Data Index: 1254201 (Open Web Text)

Max Activating Token Index: 1013

Text #12

Max Range: 2.6029. Min Range: -2.6029

Max Act: 2.5238. Min Act: -0.1549

Data Index: 7359042 (Open Web Text)

Max Activating Token Index: 1014

Text #13

Max Range: 2.6029. Min Range: -2.6029

Max Act: 2.5247. Min Act: -0.1444

Data Index: 8092555 (Open Web Text)

Max Activating Token Index: 1018

Text #14

Max Range: 2.6029. Min Range: -2.6029

Max Act: 2.5463. Min Act: -0.1246

Data Index: 4983899 (Open Web Text)

Max Activating Token Index: 1020

Text #15

Max Range: 2.6029. Min Range: -2.6029

Max Act: 2.5268. Min Act: -0.1465

Data Index: 3533543 (Open Web Text)

Max Activating Token Index: 1021

Text #16

Max Range: 2.6029. Min Range: -2.6029

Max Act: 2.5202. Min Act: -0.1025

Data Index: 2057504 (Open Web Text)

Max Activating Token Index: 1017

Text #17

Max Range: 2.6029. Min Range: -2.6029

Max Act: 2.5294. Min Act: -0.1161

Data Index: 4581807 (Open Web Text)

Max Activating Token Index: 1022

Text #18

Max Range: 2.6029. Min Range: -2.6029

Max Act: 2.5374. Min Act: -0.1418

Data Index: 1836929 (Open Web Text)

Max Activating Token Index: 1017

Text #19

Max Range: 2.6029. Min Range: -2.6029

Max Act: 2.5109. Min Act: -0.0904

Data Index: 1961431 (Open Web Text)

Max Activating Token Index: 1022