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

Dataset: Open Web Text

Neuron 2254 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: 3.6477. Min Range: -3.6477

Max Act: 3.6477. Min Act: -0.1700

Data Index: 5186994 (Open Web Text)

Max Activating Token Index: 307

Text #1

Max Range: 3.6477. Min Range: -3.6477

Max Act: 3.6064. Min Act: -0.1700

Data Index: 5585991 (Open Web Text)

Max Activating Token Index: 633

Text #2

Max Range: 3.6477. Min Range: -3.6477

Max Act: 3.5539. Min Act: -0.1700

Data Index: 8008296 (Open Web Text)

Max Activating Token Index: 598

Text #3

Max Range: 3.6477. Min Range: -3.6477

Max Act: 3.4040. Min Act: -0.1700

Data Index: 6387778 (Open Web Text)

Max Activating Token Index: 1013

Text #4

Max Range: 3.6477. Min Range: -3.6477

Max Act: 3.4636. Min Act: -0.1700

Data Index: 2107231 (Open Web Text)

Max Activating Token Index: 289

Text #5

Max Range: 3.6477. Min Range: -3.6477

Max Act: 3.4260. Min Act: -0.1700

Data Index: 1237562 (Open Web Text)

Max Activating Token Index: 679

Text #6

Max Range: 3.6477. Min Range: -3.6477

Max Act: 3.3887. Min Act: -0.1700

Data Index: 4504648 (Open Web Text)

Max Activating Token Index: 906

Text #7

Max Range: 3.6477. Min Range: -3.6477

Max Act: 3.3596. Min Act: -0.1700

Data Index: 6253009 (Open Web Text)

Max Activating Token Index: 148

Text #8

Max Range: 3.6477. Min Range: -3.6477

Max Act: 3.3551. Min Act: -0.1700

Data Index: 6179402 (Open Web Text)

Max Activating Token Index: 118

Text #9

Max Range: 3.6477. Min Range: -3.6477

Max Act: 3.3173. Min Act: -0.1700

Data Index: 3506587 (Open Web Text)

Max Activating Token Index: 524

Text #10

Max Range: 3.6477. Min Range: -3.6477

Max Act: 3.3518. Min Act: -0.1700

Data Index: 929658 (Open Web Text)

Max Activating Token Index: 450

Text #11

Max Range: 3.6477. Min Range: -3.6477

Max Act: 3.3388. Min Act: -0.1700

Data Index: 7456507 (Open Web Text)

Max Activating Token Index: 697

Text #12

Max Range: 3.6477. Min Range: -3.6477

Max Act: 3.3141. Min Act: -0.1700

Data Index: 2648439 (Open Web Text)

Max Activating Token Index: 66

Text #13

Max Range: 3.6477. Min Range: -3.6477

Max Act: 3.3175. Min Act: -0.1700

Data Index: 6062435 (Open Web Text)

Max Activating Token Index: 956

Text #14

Max Range: 3.6477. Min Range: -3.6477

Max Act: 3.3045. Min Act: -0.1700

Data Index: 3055681 (Open Web Text)

Max Activating Token Index: 356

Text #15

Max Range: 3.6477. Min Range: -3.6477

Max Act: 3.2810. Min Act: -0.1700

Data Index: 8373166 (Open Web Text)

Max Activating Token Index: 508

Text #16

Max Range: 3.6477. Min Range: -3.6477

Max Act: 3.2479. Min Act: -0.1700

Data Index: 8386134 (Open Web Text)

Max Activating Token Index: 261

Text #17

Max Range: 3.6477. Min Range: -3.6477

Max Act: 3.2381. Min Act: -0.1700

Data Index: 3340659 (Open Web Text)

Max Activating Token Index: 424

Text #18

Max Range: 3.6477. Min Range: -3.6477

Max Act: 3.2398. Min Act: -0.1700

Data Index: 6303988 (Open Web Text)

Max Activating Token Index: 346

Text #19

Max Range: 3.6477. Min Range: -3.6477

Max Act: 3.2328. Min Act: -0.1700

Data Index: 2607107 (Open Web Text)

Max Activating Token Index: 553