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

Dataset: Open Web Text

Neuron 2172 in Layer 5

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: 3.0451. Min Range: -3.0451

Max Act: 3.0451. Min Act: -0.1700

Data Index: 1175067 (Open Web Text)

Max Activating Token Index: 302

Text #1

Max Range: 3.0451. Min Range: -3.0451

Max Act: 3.0075. Min Act: -0.1700

Data Index: 8576366 (Open Web Text)

Max Activating Token Index: 271

Text #2

Max Range: 3.0451. Min Range: -3.0451

Max Act: 3.0138. Min Act: -0.1700

Data Index: 1264003 (Open Web Text)

Max Activating Token Index: 477

Text #3

Max Range: 3.0451. Min Range: -3.0451

Max Act: 2.9839. Min Act: -0.1700

Data Index: 1191897 (Open Web Text)

Max Activating Token Index: 984

Text #4

Max Range: 3.0451. Min Range: -3.0451

Max Act: 2.9783. Min Act: -0.1700

Data Index: 5952448 (Open Web Text)

Max Activating Token Index: 626

Text #5

Max Range: 3.0451. Min Range: -3.0451

Max Act: 2.9724. Min Act: -0.1700

Data Index: 774775 (Open Web Text)

Max Activating Token Index: 292

Text #6

Max Range: 3.0451. Min Range: -3.0451

Max Act: 2.9385. Min Act: -0.1700

Data Index: 8622290 (Open Web Text)

Max Activating Token Index: 262

Text #7

Max Range: 3.0451. Min Range: -3.0451

Max Act: 2.9376. Min Act: -0.1700

Data Index: 2244837 (Open Web Text)

Max Activating Token Index: 273

Text #8

Max Range: 3.0451. Min Range: -3.0451

Max Act: 2.9484. Min Act: -0.1700

Data Index: 4735404 (Open Web Text)

Max Activating Token Index: 584

Text #9

Max Range: 3.0451. Min Range: -3.0451

Max Act: 2.9447. Min Act: -0.1700

Data Index: 239312 (Open Web Text)

Max Activating Token Index: 624

Text #10

Max Range: 3.0451. Min Range: -3.0451

Max Act: 2.9459. Min Act: -0.1700

Data Index: 3015709 (Open Web Text)

Max Activating Token Index: 348

Text #11

Max Range: 3.0451. Min Range: -3.0451

Max Act: 2.9267. Min Act: -0.1700

Data Index: 4149280 (Open Web Text)

Max Activating Token Index: 874

Text #12

Max Range: 3.0451. Min Range: -3.0451

Max Act: 2.9223. Min Act: -0.1700

Data Index: 3610240 (Open Web Text)

Max Activating Token Index: 976

Text #13

Max Range: 3.0451. Min Range: -3.0451

Max Act: 2.9212. Min Act: -0.1700

Data Index: 6383371 (Open Web Text)

Max Activating Token Index: 859

Text #14

Max Range: 3.0451. Min Range: -3.0451

Max Act: 2.9160. Min Act: -0.1700

Data Index: 1775497 (Open Web Text)

Max Activating Token Index: 948

Text #15

Max Range: 3.0451. Min Range: -3.0451

Max Act: 2.9013. Min Act: -0.1700

Data Index: 4551000 (Open Web Text)

Max Activating Token Index: 686

Text #16

Max Range: 3.0451. Min Range: -3.0451

Max Act: 2.9052. Min Act: -0.1700

Data Index: 4469063 (Open Web Text)

Max Activating Token Index: 446

Text #17

Max Range: 3.0451. Min Range: -3.0451

Max Act: 2.9049. Min Act: -0.1700

Data Index: 158108 (Open Web Text)

Max Activating Token Index: 545

Text #18

Max Range: 3.0451. Min Range: -3.0451

Max Act: 2.8911. Min Act: -0.1700

Data Index: 1583166 (Open Web Text)

Max Activating Token Index: 131

Text #19

Max Range: 3.0451. Min Range: -3.0451

Max Act: 2.8791. Min Act: -0.1700

Data Index: 6714409 (Open Web Text)

Max Activating Token Index: 746