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

Dataset: Open Web Text

Neuron 1673 in Layer 2

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: 3.9313. Min Range: -3.9313

Max Act: 3.9313. Min Act: -0.1700

Data Index: 1366464 (Open Web Text)

Max Activating Token Index: 722

Text #1

Max Range: 3.9313. Min Range: -3.9313

Max Act: 3.8318. Min Act: -0.1700

Data Index: 2858356 (Open Web Text)

Max Activating Token Index: 570

Text #2

Max Range: 3.9313. Min Range: -3.9313

Max Act: 3.7852. Min Act: -0.1700

Data Index: 3328073 (Open Web Text)

Max Activating Token Index: 246

Text #3

Max Range: 3.9313. Min Range: -3.9313

Max Act: 3.7840. Min Act: -0.1700

Data Index: 8731697 (Open Web Text)

Max Activating Token Index: 11

Text #4

Max Range: 3.9313. Min Range: -3.9313

Max Act: 3.7515. Min Act: -0.1700

Data Index: 3285454 (Open Web Text)

Max Activating Token Index: 579

Text #5

Max Range: 3.9313. Min Range: -3.9313

Max Act: 3.7592. Min Act: -0.1700

Data Index: 7605527 (Open Web Text)

Max Activating Token Index: 992

Text #6

Max Range: 3.9313. Min Range: -3.9313

Max Act: 3.7682. Min Act: -0.1700

Data Index: 7831267 (Open Web Text)

Max Activating Token Index: 309

Text #7

Max Range: 3.9313. Min Range: -3.9313

Max Act: 3.7551. Min Act: -0.1700

Data Index: 3425723 (Open Web Text)

Max Activating Token Index: 692

Text #8

Max Range: 3.9313. Min Range: -3.9313

Max Act: 3.7195. Min Act: -0.1700

Data Index: 212118 (Open Web Text)

Max Activating Token Index: 332

Text #9

Max Range: 3.9313. Min Range: -3.9313

Max Act: 3.7456. Min Act: -0.1700

Data Index: 8813306 (Open Web Text)

Max Activating Token Index: 768

Text #10

Max Range: 3.9313. Min Range: -3.9313

Max Act: 3.7264. Min Act: -0.1700

Data Index: 2974635 (Open Web Text)

Max Activating Token Index: 579

Text #11

Max Range: 3.9313. Min Range: -3.9313

Max Act: 3.7504. Min Act: -0.1700

Data Index: 1305217 (Open Web Text)

Max Activating Token Index: 376

Text #12

Max Range: 3.9313. Min Range: -3.9313

Max Act: 3.7372. Min Act: -0.1700

Data Index: 2857526 (Open Web Text)

Max Activating Token Index: 763

Text #13

Max Range: 3.9313. Min Range: -3.9313

Max Act: 3.6884. Min Act: -0.1700

Data Index: 4838441 (Open Web Text)

Max Activating Token Index: 128

Text #14

Max Range: 3.9313. Min Range: -3.9313

Max Act: 3.6954. Min Act: -0.1700

Data Index: 7442225 (Open Web Text)

Max Activating Token Index: 779

Text #15

Max Range: 3.9313. Min Range: -3.9313

Max Act: 3.6992. Min Act: -0.1700

Data Index: 4592046 (Open Web Text)

Max Activating Token Index: 975

Text #16

Max Range: 3.9313. Min Range: -3.9313

Max Act: 3.6767. Min Act: -0.1700

Data Index: 702199 (Open Web Text)

Max Activating Token Index: 863

Text #17

Max Range: 3.9313. Min Range: -3.9313

Max Act: 3.6140. Min Act: -0.1700

Data Index: 8037444 (Open Web Text)

Max Activating Token Index: 503

Text #18

Max Range: 3.9313. Min Range: -3.9313

Max Act: 3.6305. Min Act: -0.1700

Data Index: 2793942 (Open Web Text)

Max Activating Token Index: 920

Text #19

Max Range: 3.9313. Min Range: -3.9313

Max Act: 3.6106. Min Act: -0.1700

Data Index: 6827276 (Open Web Text)

Max Activating Token Index: 1005