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

Dataset: Open Web Text

Neuron 2373 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: 4.5513. Min Range: -4.5513

Max Act: 4.5513. Min Act: -0.1700

Data Index: 8794733 (Open Web Text)

Max Activating Token Index: 866

Text #1

Max Range: 4.5513. Min Range: -4.5513

Max Act: 4.4523. Min Act: -0.1700

Data Index: 7884940 (Open Web Text)

Max Activating Token Index: 599

Text #2

Max Range: 4.5513. Min Range: -4.5513

Max Act: 4.1867. Min Act: -0.1700

Data Index: 3022427 (Open Web Text)

Max Activating Token Index: 962

Text #3

Max Range: 4.5513. Min Range: -4.5513

Max Act: 4.1338. Min Act: -0.1700

Data Index: 2879632 (Open Web Text)

Max Activating Token Index: 850

Text #4

Max Range: 4.5513. Min Range: -4.5513

Max Act: 4.0000. Min Act: -0.1700

Data Index: 8047283 (Open Web Text)

Max Activating Token Index: 800

Text #5

Max Range: 4.5513. Min Range: -4.5513

Max Act: 3.9668. Min Act: -0.1700

Data Index: 2008242 (Open Web Text)

Max Activating Token Index: 889

Text #6

Max Range: 4.5513. Min Range: -4.5513

Max Act: 3.9421. Min Act: -0.1695

Data Index: 5996759 (Open Web Text)

Max Activating Token Index: 1005

Text #7

Max Range: 4.5513. Min Range: -4.5513

Max Act: 3.9508. Min Act: -0.1699

Data Index: 7971849 (Open Web Text)

Max Activating Token Index: 62

Text #8

Max Range: 4.5513. Min Range: -4.5513

Max Act: 3.9645. Min Act: -0.1700

Data Index: 7503541 (Open Web Text)

Max Activating Token Index: 1005

Text #9

Max Range: 4.5513. Min Range: -4.5513

Max Act: 3.9812. Min Act: -0.1700

Data Index: 3940884 (Open Web Text)

Max Activating Token Index: 558

Text #10

Max Range: 4.5513. Min Range: -4.5513

Max Act: 3.9825. Min Act: -0.1700

Data Index: 68 (Open Web Text)

Max Activating Token Index: 495

Text #11

Max Range: 4.5513. Min Range: -4.5513

Max Act: 3.9221. Min Act: -0.1700

Data Index: 2787921 (Open Web Text)

Max Activating Token Index: 1010

Text #12

Max Range: 4.5513. Min Range: -4.5513

Max Act: 3.9531. Min Act: -0.1700

Data Index: 4311093 (Open Web Text)

Max Activating Token Index: 716

Text #13

Max Range: 4.5513. Min Range: -4.5513

Max Act: 3.8886. Min Act: -0.1700

Data Index: 1035511 (Open Web Text)

Max Activating Token Index: 924

Text #14

Max Range: 4.5513. Min Range: -4.5513

Max Act: 3.9792. Min Act: -0.1700

Data Index: 3977476 (Open Web Text)

Max Activating Token Index: 959

Text #15

Max Range: 4.5513. Min Range: -4.5513

Max Act: 3.9267. Min Act: -0.1700

Data Index: 7220493 (Open Web Text)

Max Activating Token Index: 33

Text #16

Max Range: 4.5513. Min Range: -4.5513

Max Act: 3.9246. Min Act: -0.1696

Data Index: 6869656 (Open Web Text)

Max Activating Token Index: 718

Text #17

Max Range: 4.5513. Min Range: -4.5513

Max Act: 3.9168. Min Act: -0.1700

Data Index: 6590114 (Open Web Text)

Max Activating Token Index: 422

Text #18

Max Range: 4.5513. Min Range: -4.5513

Max Act: 3.9181. Min Act: -0.1700

Data Index: 1734260 (Open Web Text)

Max Activating Token Index: 13

Text #19

Max Range: 4.5513. Min Range: -4.5513

Max Act: 3.9376. Min Act: -0.1700

Data Index: 1670492 (Open Web Text)

Max Activating Token Index: 448