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

Dataset: Open Web Text

Neuron 2443 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: 1.4110. Min Range: -1.4110

Max Act: 1.4110. Min Act: -0.1700

Data Index: 3295674 (Open Web Text)

Max Activating Token Index: 903

Text #1

Max Range: 1.4110. Min Range: -1.4110

Max Act: 1.3997. Min Act: -0.1700

Data Index: 2828055 (Open Web Text)

Max Activating Token Index: 961

Text #2

Max Range: 1.4110. Min Range: -1.4110

Max Act: 1.3862. Min Act: -0.1700

Data Index: 8402146 (Open Web Text)

Max Activating Token Index: 926

Text #3

Max Range: 1.4110. Min Range: -1.4110

Max Act: 1.3692. Min Act: -0.1700

Data Index: 4162231 (Open Web Text)

Max Activating Token Index: 907

Text #4

Max Range: 1.4110. Min Range: -1.4110

Max Act: 1.3527. Min Act: -0.1699

Data Index: 6328324 (Open Web Text)

Max Activating Token Index: 853

Text #5

Max Range: 1.4110. Min Range: -1.4110

Max Act: 1.3609. Min Act: -0.1700

Data Index: 1778977 (Open Web Text)

Max Activating Token Index: 920

Text #6

Max Range: 1.4110. Min Range: -1.4110

Max Act: 1.3518. Min Act: -0.1700

Data Index: 6300828 (Open Web Text)

Max Activating Token Index: 940

Text #7

Max Range: 1.4110. Min Range: -1.4110

Max Act: 1.3563. Min Act: -0.1699

Data Index: 344974 (Open Web Text)

Max Activating Token Index: 828

Text #8

Max Range: 1.4110. Min Range: -1.4110

Max Act: 1.3415. Min Act: -0.1698

Data Index: 8470431 (Open Web Text)

Max Activating Token Index: 894

Text #9

Max Range: 1.4110. Min Range: -1.4110

Max Act: 1.3425. Min Act: -0.1700

Data Index: 528997 (Open Web Text)

Max Activating Token Index: 889

Text #10

Max Range: 1.4110. Min Range: -1.4110

Max Act: 1.3472. Min Act: -0.1699

Data Index: 5645452 (Open Web Text)

Max Activating Token Index: 814

Text #11

Max Range: 1.4110. Min Range: -1.4110

Max Act: 1.3577. Min Act: -0.1700

Data Index: 4044195 (Open Web Text)

Max Activating Token Index: 923

Text #12

Max Range: 1.4110. Min Range: -1.4110

Max Act: 1.3355. Min Act: -0.1700

Data Index: 5549876 (Open Web Text)

Max Activating Token Index: 898

Text #13

Max Range: 1.4110. Min Range: -1.4110

Max Act: 1.3478. Min Act: -0.1700

Data Index: 6498754 (Open Web Text)

Max Activating Token Index: 847

Text #14

Max Range: 1.4110. Min Range: -1.4110

Max Act: 1.3379. Min Act: -0.1700

Data Index: 6513659 (Open Web Text)

Max Activating Token Index: 899

Text #15

Max Range: 1.4110. Min Range: -1.4110

Max Act: 1.3323. Min Act: -0.1700

Data Index: 3605784 (Open Web Text)

Max Activating Token Index: 885

Text #16

Max Range: 1.4110. Min Range: -1.4110

Max Act: 1.3428. Min Act: -0.1697

Data Index: 6730805 (Open Web Text)

Max Activating Token Index: 917

Text #17

Max Range: 1.4110. Min Range: -1.4110

Max Act: 1.3437. Min Act: -0.1700

Data Index: 5549864 (Open Web Text)

Max Activating Token Index: 894

Text #18

Max Range: 1.4110. Min Range: -1.4110

Max Act: 1.3362. Min Act: -0.1700

Data Index: 5936777 (Open Web Text)

Max Activating Token Index: 932

Text #19

Max Range: 1.4110. Min Range: -1.4110

Max Act: 1.3264. Min Act: -0.1700

Data Index: 4990973 (Open Web Text)

Max Activating Token Index: 899