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

Dataset: Open Web Text

Neuron 198 in Layer 4

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: 5.4640. Min Range: -5.4640

Max Act: 5.4640. Min Act: -0.1700

Data Index: 7831575 (Open Web Text)

Max Activating Token Index: 80

Text #1

Max Range: 5.4640. Min Range: -5.4640

Max Act: 5.2916. Min Act: -0.1700

Data Index: 713226 (Open Web Text)

Max Activating Token Index: 817

Text #2

Max Range: 5.4640. Min Range: -5.4640

Max Act: 5.3118. Min Act: -0.1700

Data Index: 1242504 (Open Web Text)

Max Activating Token Index: 145

Text #3

Max Range: 5.4640. Min Range: -5.4640

Max Act: 5.2567. Min Act: -0.1700

Data Index: 2143715 (Open Web Text)

Max Activating Token Index: 404

Text #4

Max Range: 5.4640. Min Range: -5.4640

Max Act: 5.2164. Min Act: -0.1700

Data Index: 3603409 (Open Web Text)

Max Activating Token Index: 793

Text #5

Max Range: 5.4640. Min Range: -5.4640

Max Act: 5.2849. Min Act: -0.1700

Data Index: 5422980 (Open Web Text)

Max Activating Token Index: 532

Text #6

Max Range: 5.4640. Min Range: -5.4640

Max Act: 5.2542. Min Act: -0.1700

Data Index: 4377071 (Open Web Text)

Max Activating Token Index: 80

Text #7

Max Range: 5.4640. Min Range: -5.4640

Max Act: 5.2100. Min Act: -0.1700

Data Index: 3401234 (Open Web Text)

Max Activating Token Index: 226

Text #8

Max Range: 5.4640. Min Range: -5.4640

Max Act: 5.2121. Min Act: -0.1700

Data Index: 1026290 (Open Web Text)

Max Activating Token Index: 115

Text #9

Max Range: 5.4640. Min Range: -5.4640

Max Act: 5.2061. Min Act: -0.1700

Data Index: 501450 (Open Web Text)

Max Activating Token Index: 17

Text #10

Max Range: 5.4640. Min Range: -5.4640

Max Act: 5.2446. Min Act: -0.1700

Data Index: 5699618 (Open Web Text)

Max Activating Token Index: 35

Text #11

Max Range: 5.4640. Min Range: -5.4640

Max Act: 5.2574. Min Act: -0.1700

Data Index: 6843997 (Open Web Text)

Max Activating Token Index: 513

Text #12

Max Range: 5.4640. Min Range: -5.4640

Max Act: 5.2029. Min Act: -0.1700

Data Index: 1314463 (Open Web Text)

Max Activating Token Index: 9

Text #13

Max Range: 5.4640. Min Range: -5.4640

Max Act: 5.1654. Min Act: -0.1700

Data Index: 8701286 (Open Web Text)

Max Activating Token Index: 812

Text #14

Max Range: 5.4640. Min Range: -5.4640

Max Act: 5.2014. Min Act: -0.1700

Data Index: 5743488 (Open Web Text)

Max Activating Token Index: 861

Text #15

Max Range: 5.4640. Min Range: -5.4640

Max Act: 5.1938. Min Act: -0.1700

Data Index: 5723917 (Open Web Text)

Max Activating Token Index: 198

Text #16

Max Range: 5.4640. Min Range: -5.4640

Max Act: 5.2177. Min Act: -0.1700

Data Index: 5675864 (Open Web Text)

Max Activating Token Index: 284

Text #17

Max Range: 5.4640. Min Range: -5.4640

Max Act: 5.2020. Min Act: -0.1700

Data Index: 7275948 (Open Web Text)

Max Activating Token Index: 383

Text #18

Max Range: 5.4640. Min Range: -5.4640

Max Act: 5.1971. Min Act: -0.1700

Data Index: 6979282 (Open Web Text)

Max Activating Token Index: 825

Text #19

Max Range: 5.4640. Min Range: -5.4640

Max Act: 5.1756. Min Act: -0.1700

Data Index: 3270761 (Open Web Text)

Max Activating Token Index: 398