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

Dataset: Open Web Text

Neuron 996 in Layer 2

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: 4.3272. Min Range: -4.3272

Max Act: 4.3199. Min Act: -0.1700

Data Index: 1845351 (Open Web Text)

Max Activating Token Index: 460

Text #1

Max Range: 4.3272. Min Range: -4.3272

Max Act: 4.3272. Min Act: -0.1700

Data Index: 2392197 (Open Web Text)

Max Activating Token Index: 977

Text #2

Max Range: 4.3272. Min Range: -4.3272

Max Act: 4.2813. Min Act: -0.1700

Data Index: 5925189 (Open Web Text)

Max Activating Token Index: 672

Text #3

Max Range: 4.3272. Min Range: -4.3272

Max Act: 4.2661. Min Act: -0.1700

Data Index: 4357772 (Open Web Text)

Max Activating Token Index: 669

Text #4

Max Range: 4.3272. Min Range: -4.3272

Max Act: 4.2682. Min Act: -0.1700

Data Index: 3760999 (Open Web Text)

Max Activating Token Index: 208

Text #5

Max Range: 4.3272. Min Range: -4.3272

Max Act: 4.2315. Min Act: -0.1700

Data Index: 3760398 (Open Web Text)

Max Activating Token Index: 697

Text #6

Max Range: 4.3272. Min Range: -4.3272

Max Act: 4.1876. Min Act: -0.1700

Data Index: 3353873 (Open Web Text)

Max Activating Token Index: 467

Text #7

Max Range: 4.3272. Min Range: -4.3272

Max Act: 4.2022. Min Act: -0.1700

Data Index: 7072737 (Open Web Text)

Max Activating Token Index: 545

Text #8

Max Range: 4.3272. Min Range: -4.3272

Max Act: 4.1596. Min Act: -0.1700

Data Index: 1039492 (Open Web Text)

Max Activating Token Index: 414

Text #9

Max Range: 4.3272. Min Range: -4.3272

Max Act: 4.1958. Min Act: -0.1700

Data Index: 4258107 (Open Web Text)

Max Activating Token Index: 583

Text #10

Max Range: 4.3272. Min Range: -4.3272

Max Act: 4.1540. Min Act: -0.1700

Data Index: 740053 (Open Web Text)

Max Activating Token Index: 995

Text #11

Max Range: 4.3272. Min Range: -4.3272

Max Act: 4.1843. Min Act: -0.1700

Data Index: 4040610 (Open Web Text)

Max Activating Token Index: 515

Text #12

Max Range: 4.3272. Min Range: -4.3272

Max Act: 4.1481. Min Act: -0.1700

Data Index: 61098 (Open Web Text)

Max Activating Token Index: 683

Text #13

Max Range: 4.3272. Min Range: -4.3272

Max Act: 4.1478. Min Act: -0.1700

Data Index: 5245449 (Open Web Text)

Max Activating Token Index: 580

Text #14

Max Range: 4.3272. Min Range: -4.3272

Max Act: 4.1216. Min Act: -0.1700

Data Index: 7892655 (Open Web Text)

Max Activating Token Index: 635

Text #15

Max Range: 4.3272. Min Range: -4.3272

Max Act: 4.1156. Min Act: -0.1700

Data Index: 1295910 (Open Web Text)

Max Activating Token Index: 489

Text #16

Max Range: 4.3272. Min Range: -4.3272

Max Act: 4.1386. Min Act: -0.1700

Data Index: 3283788 (Open Web Text)

Max Activating Token Index: 476

Text #17

Max Range: 4.3272. Min Range: -4.3272

Max Act: 4.1224. Min Act: -0.1700

Data Index: 945889 (Open Web Text)

Max Activating Token Index: 568

Text #18

Max Range: 4.3272. Min Range: -4.3272

Max Act: 4.0848. Min Act: -0.1700

Data Index: 3462509 (Open Web Text)

Max Activating Token Index: 71

Text #19

Max Range: 4.3272. Min Range: -4.3272

Max Act: 4.0905. Min Act: -0.1698

Data Index: 6088531 (Open Web Text)

Max Activating Token Index: 168