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

Dataset: Open Web Text

Neuron 577 in Layer 6

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: 4.4382. Min Range: -4.4382

Max Act: 4.4382. Min Act: -0.1700

Data Index: 5243818 (Open Web Text)

Max Activating Token Index: 557

Text #1

Max Range: 4.4382. Min Range: -4.4382

Max Act: 4.3873. Min Act: -0.1700

Data Index: 7327443 (Open Web Text)

Max Activating Token Index: 413

Text #2

Max Range: 4.4382. Min Range: -4.4382

Max Act: 4.3828. Min Act: -0.1700

Data Index: 3711726 (Open Web Text)

Max Activating Token Index: 670

Text #3

Max Range: 4.4382. Min Range: -4.4382

Max Act: 4.2958. Min Act: -0.1700

Data Index: 5970266 (Open Web Text)

Max Activating Token Index: 488

Text #4

Max Range: 4.4382. Min Range: -4.4382

Max Act: 4.3031. Min Act: -0.1700

Data Index: 274155 (Open Web Text)

Max Activating Token Index: 901

Text #5

Max Range: 4.4382. Min Range: -4.4382

Max Act: 4.2983. Min Act: -0.1700

Data Index: 2778456 (Open Web Text)

Max Activating Token Index: 218

Text #6

Max Range: 4.4382. Min Range: -4.4382

Max Act: 4.2732. Min Act: -0.1700

Data Index: 2637226 (Open Web Text)

Max Activating Token Index: 198

Text #7

Max Range: 4.4382. Min Range: -4.4382

Max Act: 4.2872. Min Act: -0.1700

Data Index: 7964583 (Open Web Text)

Max Activating Token Index: 149

Text #8

Max Range: 4.4382. Min Range: -4.4382

Max Act: 4.2585. Min Act: -0.1700

Data Index: 5375657 (Open Web Text)

Max Activating Token Index: 592

Text #9

Max Range: 4.4382. Min Range: -4.4382

Max Act: 4.2843. Min Act: -0.1700

Data Index: 4667868 (Open Web Text)

Max Activating Token Index: 81

Text #10

Max Range: 4.4382. Min Range: -4.4382

Max Act: 4.2537. Min Act: -0.1700

Data Index: 6243080 (Open Web Text)

Max Activating Token Index: 1002

Text #11

Max Range: 4.4382. Min Range: -4.4382

Max Act: 4.2576. Min Act: -0.1700

Data Index: 5046094 (Open Web Text)

Max Activating Token Index: 531

Text #12

Max Range: 4.4382. Min Range: -4.4382

Max Act: 4.2513. Min Act: -0.1700

Data Index: 6712604 (Open Web Text)

Max Activating Token Index: 575

Text #13

Max Range: 4.4382. Min Range: -4.4382

Max Act: 4.2681. Min Act: -0.1700

Data Index: 973415 (Open Web Text)

Max Activating Token Index: 279

Text #14

Max Range: 4.4382. Min Range: -4.4382

Max Act: 4.2758. Min Act: -0.1700

Data Index: 3046543 (Open Web Text)

Max Activating Token Index: 978

Text #15

Max Range: 4.4382. Min Range: -4.4382

Max Act: 4.2326. Min Act: -0.1700

Data Index: 7677879 (Open Web Text)

Max Activating Token Index: 76

Text #16

Max Range: 4.4382. Min Range: -4.4382

Max Act: 4.2308. Min Act: -0.1700

Data Index: 7191114 (Open Web Text)

Max Activating Token Index: 926

Text #17

Max Range: 4.4382. Min Range: -4.4382

Max Act: 4.2469. Min Act: -0.1700

Data Index: 6795797 (Open Web Text)

Max Activating Token Index: 946

Text #18

Max Range: 4.4382. Min Range: -4.4382

Max Act: 4.2395. Min Act: -0.1700

Data Index: 6446803 (Open Web Text)

Max Activating Token Index: 1006

Text #19

Max Range: 4.4382. Min Range: -4.4382

Max Act: 4.2186. Min Act: -0.1700

Data Index: 4129566 (Open Web Text)

Max Activating Token Index: 565