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

Dataset: Open Web Text

Neuron 2108 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: 1.0863. Min Range: -1.0863

Max Act: 1.0863. Min Act: -0.1700

Data Index: 8481894 (Open Web Text)

Max Activating Token Index: 565

Text #1

Max Range: 1.0863. Min Range: -1.0863

Max Act: 1.0606. Min Act: -0.1700

Data Index: 5187251 (Open Web Text)

Max Activating Token Index: 270

Text #2

Max Range: 1.0863. Min Range: -1.0863

Max Act: 1.0201. Min Act: -0.1690

Data Index: 2192207 (Open Web Text)

Max Activating Token Index: 938

Text #3

Max Range: 1.0863. Min Range: -1.0863

Max Act: 1.0011. Min Act: -0.1700

Data Index: 5180443 (Open Web Text)

Max Activating Token Index: 847

Text #4

Max Range: 1.0863. Min Range: -1.0863

Max Act: 0.9989. Min Act: -0.1694

Data Index: 2897165 (Open Web Text)

Max Activating Token Index: 429

Text #5

Max Range: 1.0863. Min Range: -1.0863

Max Act: 0.9923. Min Act: -0.1688

Data Index: 2346883 (Open Web Text)

Max Activating Token Index: 336

Text #6

Max Range: 1.0863. Min Range: -1.0863

Max Act: 0.9980. Min Act: -0.1700

Data Index: 5780189 (Open Web Text)

Max Activating Token Index: 964

Text #7

Max Range: 1.0863. Min Range: -1.0863

Max Act: 0.9788. Min Act: -0.1699

Data Index: 5424737 (Open Web Text)

Max Activating Token Index: 127

Text #8

Max Range: 1.0863. Min Range: -1.0863

Max Act: 0.9558. Min Act: -0.1700

Data Index: 3405804 (Open Web Text)

Max Activating Token Index: 854

Text #9

Max Range: 1.0863. Min Range: -1.0863

Max Act: 0.9408. Min Act: -0.1698

Data Index: 5886290 (Open Web Text)

Max Activating Token Index: 616

Text #10

Max Range: 1.0863. Min Range: -1.0863

Max Act: 0.9448. Min Act: -0.1698

Data Index: 3235241 (Open Web Text)

Max Activating Token Index: 559

Text #11

Max Range: 1.0863. Min Range: -1.0863

Max Act: 0.9483. Min Act: -0.1685

Data Index: 7279872 (Open Web Text)

Max Activating Token Index: 77

Text #12

Max Range: 1.0863. Min Range: -1.0863

Max Act: 0.9347. Min Act: -0.1694

Data Index: 764306 (Open Web Text)

Max Activating Token Index: 128

Text #13

Max Range: 1.0863. Min Range: -1.0863

Max Act: 0.9324. Min Act: -0.1699

Data Index: 7272493 (Open Web Text)

Max Activating Token Index: 347

Text #14

Max Range: 1.0863. Min Range: -1.0863

Max Act: 0.9171. Min Act: -0.1699

Data Index: 5730515 (Open Web Text)

Max Activating Token Index: 972

Text #15

Max Range: 1.0863. Min Range: -1.0863

Max Act: 0.9362. Min Act: -0.1700

Data Index: 178110 (Open Web Text)

Max Activating Token Index: 335

Text #16

Max Range: 1.0863. Min Range: -1.0863

Max Act: 0.9372. Min Act: -0.1699

Data Index: 2563004 (Open Web Text)

Max Activating Token Index: 654

Text #17

Max Range: 1.0863. Min Range: -1.0863

Max Act: 0.9434. Min Act: -0.1700

Data Index: 7220878 (Open Web Text)

Max Activating Token Index: 121

Text #18

Max Range: 1.0863. Min Range: -1.0863

Max Act: 0.9185. Min Act: -0.1699

Data Index: 832018 (Open Web Text)

Max Activating Token Index: 21

Text #19

Max Range: 1.0863. Min Range: -1.0863

Max Act: 0.9193. Min Act: -0.1700

Data Index: 2322239 (Open Web Text)

Max Activating Token Index: 506