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

Dataset: Open Web Text

Neuron 179 in Layer 6

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: 5.1222. Min Range: -5.1222

Max Act: 5.1222. Min Act: -0.1700

Data Index: 7359769 (Open Web Text)

Max Activating Token Index: 51

Text #1

Max Range: 5.1222. Min Range: -5.1222

Max Act: 5.0551. Min Act: -0.1700

Data Index: 330472 (Open Web Text)

Max Activating Token Index: 481

Text #2

Max Range: 5.1222. Min Range: -5.1222

Max Act: 5.0610. Min Act: -0.1700

Data Index: 7127524 (Open Web Text)

Max Activating Token Index: 949

Text #3

Max Range: 5.1222. Min Range: -5.1222

Max Act: 4.9827. Min Act: -0.1700

Data Index: 4303468 (Open Web Text)

Max Activating Token Index: 404

Text #4

Max Range: 5.1222. Min Range: -5.1222

Max Act: 4.9365. Min Act: -0.1700

Data Index: 8229019 (Open Web Text)

Max Activating Token Index: 661

Text #5

Max Range: 5.1222. Min Range: -5.1222

Max Act: 4.9605. Min Act: -0.1700

Data Index: 3391661 (Open Web Text)

Max Activating Token Index: 218

Text #6

Max Range: 5.1222. Min Range: -5.1222

Max Act: 4.8973. Min Act: -0.1700

Data Index: 3685082 (Open Web Text)

Max Activating Token Index: 584

Text #7

Max Range: 5.1222. Min Range: -5.1222

Max Act: 4.8899. Min Act: -0.1700

Data Index: 6744204 (Open Web Text)

Max Activating Token Index: 171

Text #8

Max Range: 5.1222. Min Range: -5.1222

Max Act: 4.9253. Min Act: -0.1700

Data Index: 5831199 (Open Web Text)

Max Activating Token Index: 108

Text #9

Max Range: 5.1222. Min Range: -5.1222

Max Act: 4.8892. Min Act: -0.1700

Data Index: 7162788 (Open Web Text)

Max Activating Token Index: 454

Text #10

Max Range: 5.1222. Min Range: -5.1222

Max Act: 4.9026. Min Act: -0.1700

Data Index: 4437432 (Open Web Text)

Max Activating Token Index: 621

Text #11

Max Range: 5.1222. Min Range: -5.1222

Max Act: 4.8777. Min Act: -0.1700

Data Index: 2067417 (Open Web Text)

Max Activating Token Index: 111

Text #12

Max Range: 5.1222. Min Range: -5.1222

Max Act: 4.8689. Min Act: -0.1700

Data Index: 5193795 (Open Web Text)

Max Activating Token Index: 307

Text #13

Max Range: 5.1222. Min Range: -5.1222

Max Act: 4.8222. Min Act: -0.1700

Data Index: 375223 (Open Web Text)

Max Activating Token Index: 549

Text #14

Max Range: 5.1222. Min Range: -5.1222

Max Act: 4.8471. Min Act: -0.1700

Data Index: 609519 (Open Web Text)

Max Activating Token Index: 414

Text #15

Max Range: 5.1222. Min Range: -5.1222

Max Act: 4.8509. Min Act: -0.1700

Data Index: 7818550 (Open Web Text)

Max Activating Token Index: 827

Text #16

Max Range: 5.1222. Min Range: -5.1222

Max Act: 4.8515. Min Act: -0.1700

Data Index: 7000453 (Open Web Text)

Max Activating Token Index: 881

Text #17

Max Range: 5.1222. Min Range: -5.1222

Max Act: 4.8037. Min Act: -0.1700

Data Index: 6686185 (Open Web Text)

Max Activating Token Index: 427

Text #18

Max Range: 5.1222. Min Range: -5.1222

Max Act: 4.8218. Min Act: -0.1700

Data Index: 3010523 (Open Web Text)

Max Activating Token Index: 223

Text #19

Max Range: 5.1222. Min Range: -5.1222

Max Act: 4.8053. Min Act: -0.1700

Data Index: 3018996 (Open Web Text)

Max Activating Token Index: 200