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

Dataset: Open Web Text

Neuron 1333 in Layer 0

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: 1.7489. Min Range: -1.7489

Max Act: 1.7489. Min Act: -0.0921

Data Index: 190334 (Open Web Text)

Max Activating Token Index: 1002

Text #1

Max Range: 1.7489. Min Range: -1.7489

Max Act: 1.7273. Min Act: -0.0539

Data Index: 5364278 (Open Web Text)

Max Activating Token Index: 744

Text #2

Max Range: 1.7489. Min Range: -1.7489

Max Act: 1.7385. Min Act: -0.0919

Data Index: 7391800 (Open Web Text)

Max Activating Token Index: 686

Text #3

Max Range: 1.7489. Min Range: -1.7489

Max Act: 1.7302. Min Act: -0.1018

Data Index: 3465889 (Open Web Text)

Max Activating Token Index: 630

Text #4

Max Range: 1.7489. Min Range: -1.7489

Max Act: 1.7241. Min Act: -0.0673

Data Index: 4412781 (Open Web Text)

Max Activating Token Index: 619

Text #5

Max Range: 1.7489. Min Range: -1.7489

Max Act: 1.7082. Min Act: -0.1033

Data Index: 5183109 (Open Web Text)

Max Activating Token Index: 304

Text #6

Max Range: 1.7489. Min Range: -1.7489

Max Act: 1.7070. Min Act: -0.1014

Data Index: 7267217 (Open Web Text)

Max Activating Token Index: 616

Text #7

Max Range: 1.7489. Min Range: -1.7489

Max Act: 1.7090. Min Act: -0.1513

Data Index: 6621509 (Open Web Text)

Max Activating Token Index: 917

Text #8

Max Range: 1.7489. Min Range: -1.7489

Max Act: 1.6924. Min Act: -0.0897

Data Index: 7518164 (Open Web Text)

Max Activating Token Index: 629

Text #9

Max Range: 1.7489. Min Range: -1.7489

Max Act: 1.6993. Min Act: -0.1142

Data Index: 1193599 (Open Web Text)

Max Activating Token Index: 161

Text #10

Max Range: 1.7489. Min Range: -1.7489

Max Act: 1.7015. Min Act: -0.0586

Data Index: 3959638 (Open Web Text)

Max Activating Token Index: 601

Text #11

Max Range: 1.7489. Min Range: -1.7489

Max Act: 1.6977. Min Act: -0.1062

Data Index: 8354527 (Open Web Text)

Max Activating Token Index: 677

Text #12

Max Range: 1.7489. Min Range: -1.7489

Max Act: 1.7026. Min Act: -0.0626

Data Index: 1735232 (Open Web Text)

Max Activating Token Index: 1022

Text #13

Max Range: 1.7489. Min Range: -1.7489

Max Act: 1.7076. Min Act: -0.0985

Data Index: 5697992 (Open Web Text)

Max Activating Token Index: 297

Text #14

Max Range: 1.7489. Min Range: -1.7489

Max Act: 1.6947. Min Act: -0.0371

Data Index: 2011887 (Open Web Text)

Max Activating Token Index: 210

Text #15

Max Range: 1.7489. Min Range: -1.7489

Max Act: 1.6994. Min Act: -0.0844

Data Index: 3442231 (Open Web Text)

Max Activating Token Index: 394

Text #16

Max Range: 1.7489. Min Range: -1.7489

Max Act: 1.6897. Min Act: -0.1420

Data Index: 1375774 (Open Web Text)

Max Activating Token Index: 630

Text #17

Max Range: 1.7489. Min Range: -1.7489

Max Act: 1.6774. Min Act: -0.1000

Data Index: 3994635 (Open Web Text)

Max Activating Token Index: 969

Text #18

Max Range: 1.7489. Min Range: -1.7489

Max Act: 1.6891. Min Act: -0.0869

Data Index: 4681642 (Open Web Text)

Max Activating Token Index: 561

Text #19

Max Range: 1.7489. Min Range: -1.7489

Max Act: 1.6942. Min Act: -0.1182

Data Index: 2507558 (Open Web Text)

Max Activating Token Index: 489