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

Dataset: Open Web Text

Neuron 132 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: 3.7438. Min Range: -3.7438

Max Act: 3.7438. Min Act: -0.1700

Data Index: 2069712 (Open Web Text)

Max Activating Token Index: 26

Text #1

Max Range: 3.7438. Min Range: -3.7438

Max Act: 3.6334. Min Act: -0.1700

Data Index: 2069711 (Open Web Text)

Max Activating Token Index: 38

Text #2

Max Range: 3.7438. Min Range: -3.7438

Max Act: 3.4358. Min Act: -0.1700

Data Index: 5098182 (Open Web Text)

Max Activating Token Index: 355

Text #3

Max Range: 3.7438. Min Range: -3.7438

Max Act: 3.4369. Min Act: -0.1700

Data Index: 2069710 (Open Web Text)

Max Activating Token Index: 791

Text #4

Max Range: 3.7438. Min Range: -3.7438

Max Act: 3.4421. Min Act: -0.1700

Data Index: 8318789 (Open Web Text)

Max Activating Token Index: 527

Text #5

Max Range: 3.7438. Min Range: -3.7438

Max Act: 3.3928. Min Act: -0.1700

Data Index: 8148431 (Open Web Text)

Max Activating Token Index: 711

Text #6

Max Range: 3.7438. Min Range: -3.7438

Max Act: 3.3400. Min Act: -0.1700

Data Index: 193525 (Open Web Text)

Max Activating Token Index: 295

Text #7

Max Range: 3.7438. Min Range: -3.7438

Max Act: 3.2907. Min Act: -0.1700

Data Index: 3006434 (Open Web Text)

Max Activating Token Index: 265

Text #8

Max Range: 3.7438. Min Range: -3.7438

Max Act: 3.3034. Min Act: -0.1700

Data Index: 3866135 (Open Web Text)

Max Activating Token Index: 404

Text #9

Max Range: 3.7438. Min Range: -3.7438

Max Act: 3.2925. Min Act: -0.1700

Data Index: 3244785 (Open Web Text)

Max Activating Token Index: 991

Text #10

Max Range: 3.7438. Min Range: -3.7438

Max Act: 3.2941. Min Act: -0.1700

Data Index: 3244782 (Open Web Text)

Max Activating Token Index: 185

Text #11

Max Range: 3.7438. Min Range: -3.7438

Max Act: 3.2572. Min Act: -0.1700

Data Index: 3244789 (Open Web Text)

Max Activating Token Index: 839

Text #12

Max Range: 3.7438. Min Range: -3.7438

Max Act: 3.2682. Min Act: -0.1700

Data Index: 6439675 (Open Web Text)

Max Activating Token Index: 256

Text #13

Max Range: 3.7438. Min Range: -3.7438

Max Act: 3.2560. Min Act: -0.1700

Data Index: 3978741 (Open Web Text)

Max Activating Token Index: 856

Text #14

Max Range: 3.7438. Min Range: -3.7438

Max Act: 3.2762. Min Act: -0.1700

Data Index: 74392 (Open Web Text)

Max Activating Token Index: 204

Text #15

Max Range: 3.7438. Min Range: -3.7438

Max Act: 3.2411. Min Act: -0.1700

Data Index: 1479582 (Open Web Text)

Max Activating Token Index: 896

Text #16

Max Range: 3.7438. Min Range: -3.7438

Max Act: 3.2582. Min Act: -0.1700

Data Index: 7375787 (Open Web Text)

Max Activating Token Index: 699

Text #17

Max Range: 3.7438. Min Range: -3.7438

Max Act: 3.2581. Min Act: -0.1700

Data Index: 3207430 (Open Web Text)

Max Activating Token Index: 697

Text #18

Max Range: 3.7438. Min Range: -3.7438

Max Act: 3.2436. Min Act: -0.1700

Data Index: 3244786 (Open Web Text)

Max Activating Token Index: 375

Text #19

Max Range: 3.7438. Min Range: -3.7438

Max Act: 3.2366. Min Act: -0.1700

Data Index: 4007586 (Open Web Text)

Max Activating Token Index: 418