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

Dataset: Open Web Text

Neuron 987 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: 3.4036. Min Range: -3.4036

Max Act: 3.4036. Min Act: -0.1700

Data Index: 5612958 (Open Web Text)

Max Activating Token Index: 276

Text #1

Max Range: 3.4036. Min Range: -3.4036

Max Act: 3.3918. Min Act: -0.1700

Data Index: 2166649 (Open Web Text)

Max Activating Token Index: 485

Text #2

Max Range: 3.4036. Min Range: -3.4036

Max Act: 3.3894. Min Act: -0.1700

Data Index: 902338 (Open Web Text)

Max Activating Token Index: 607

Text #3

Max Range: 3.4036. Min Range: -3.4036

Max Act: 3.3903. Min Act: -0.1700

Data Index: 4379254 (Open Web Text)

Max Activating Token Index: 254

Text #4

Max Range: 3.4036. Min Range: -3.4036

Max Act: 3.3930. Min Act: -0.1700

Data Index: 4894756 (Open Web Text)

Max Activating Token Index: 527

Text #5

Max Range: 3.4036. Min Range: -3.4036

Max Act: 3.3551. Min Act: -0.1700

Data Index: 5290700 (Open Web Text)

Max Activating Token Index: 701

Text #6

Max Range: 3.4036. Min Range: -3.4036

Max Act: 3.3473. Min Act: -0.1700

Data Index: 2482119 (Open Web Text)

Max Activating Token Index: 590

Text #7

Max Range: 3.4036. Min Range: -3.4036

Max Act: 3.3327. Min Act: -0.1700

Data Index: 7580018 (Open Web Text)

Max Activating Token Index: 4

Text #8

Max Range: 3.4036. Min Range: -3.4036

Max Act: 3.3446. Min Act: -0.1700

Data Index: 5745470 (Open Web Text)

Max Activating Token Index: 51

Text #9

Max Range: 3.4036. Min Range: -3.4036

Max Act: 3.3004. Min Act: -0.1700

Data Index: 6423919 (Open Web Text)

Max Activating Token Index: 110

Text #10

Max Range: 3.4036. Min Range: -3.4036

Max Act: 3.3009. Min Act: -0.1700

Data Index: 7820968 (Open Web Text)

Max Activating Token Index: 3

Text #11

Max Range: 3.4036. Min Range: -3.4036

Max Act: 3.3028. Min Act: -0.1700

Data Index: 1651568 (Open Web Text)

Max Activating Token Index: 582

Text #12

Max Range: 3.4036. Min Range: -3.4036

Max Act: 3.2851. Min Act: -0.1700

Data Index: 5102250 (Open Web Text)

Max Activating Token Index: 331

Text #13

Max Range: 3.4036. Min Range: -3.4036

Max Act: 3.3035. Min Act: -0.1700

Data Index: 42441 (Open Web Text)

Max Activating Token Index: 315

Text #14

Max Range: 3.4036. Min Range: -3.4036

Max Act: 3.2736. Min Act: -0.1700

Data Index: 1222682 (Open Web Text)

Max Activating Token Index: 5

Text #15

Max Range: 3.4036. Min Range: -3.4036

Max Act: 3.2607. Min Act: -0.1700

Data Index: 5787843 (Open Web Text)

Max Activating Token Index: 204

Text #16

Max Range: 3.4036. Min Range: -3.4036

Max Act: 3.2924. Min Act: -0.1700

Data Index: 4100446 (Open Web Text)

Max Activating Token Index: 724

Text #17

Max Range: 3.4036. Min Range: -3.4036

Max Act: 3.2832. Min Act: -0.1700

Data Index: 8380911 (Open Web Text)

Max Activating Token Index: 85

Text #18

Max Range: 3.4036. Min Range: -3.4036

Max Act: 3.2718. Min Act: -0.1700

Data Index: 7062675 (Open Web Text)

Max Activating Token Index: 52

Text #19

Max Range: 3.4036. Min Range: -3.4036

Max Act: 3.2793. Min Act: -0.1700

Data Index: 7771445 (Open Web Text)

Max Activating Token Index: 641