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

Dataset: Open Web Text

Neuron 3003 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: 3.9910. Min Range: -3.9910

Max Act: 3.9910. Min Act: -0.1700

Data Index: 2406616 (Open Web Text)

Max Activating Token Index: 714

Text #1

Max Range: 3.9910. Min Range: -3.9910

Max Act: 3.9379. Min Act: -0.1700

Data Index: 2035164 (Open Web Text)

Max Activating Token Index: 763

Text #2

Max Range: 3.9910. Min Range: -3.9910

Max Act: 3.9400. Min Act: -0.1700

Data Index: 8213680 (Open Web Text)

Max Activating Token Index: 703

Text #3

Max Range: 3.9910. Min Range: -3.9910

Max Act: 3.8487. Min Act: -0.1700

Data Index: 5948259 (Open Web Text)

Max Activating Token Index: 751

Text #4

Max Range: 3.9910. Min Range: -3.9910

Max Act: 3.8790. Min Act: -0.1700

Data Index: 3277850 (Open Web Text)

Max Activating Token Index: 536

Text #5

Max Range: 3.9910. Min Range: -3.9910

Max Act: 3.8124. Min Act: -0.1700

Data Index: 3308392 (Open Web Text)

Max Activating Token Index: 691

Text #6

Max Range: 3.9910. Min Range: -3.9910

Max Act: 3.8209. Min Act: -0.1700

Data Index: 4877810 (Open Web Text)

Max Activating Token Index: 426

Text #7

Max Range: 3.9910. Min Range: -3.9910

Max Act: 3.8668. Min Act: -0.1700

Data Index: 4948372 (Open Web Text)

Max Activating Token Index: 527

Text #8

Max Range: 3.9910. Min Range: -3.9910

Max Act: 3.8223. Min Act: -0.1700

Data Index: 2138630 (Open Web Text)

Max Activating Token Index: 1006

Text #9

Max Range: 3.9910. Min Range: -3.9910

Max Act: 3.8857. Min Act: -0.1700

Data Index: 86922 (Open Web Text)

Max Activating Token Index: 566

Text #10

Max Range: 3.9910. Min Range: -3.9910

Max Act: 3.7688. Min Act: -0.1700

Data Index: 6182330 (Open Web Text)

Max Activating Token Index: 276

Text #11

Max Range: 3.9910. Min Range: -3.9910

Max Act: 3.7468. Min Act: -0.1700

Data Index: 3750522 (Open Web Text)

Max Activating Token Index: 297

Text #12

Max Range: 3.9910. Min Range: -3.9910

Max Act: 3.7378. Min Act: -0.1700

Data Index: 1882096 (Open Web Text)

Max Activating Token Index: 976

Text #13

Max Range: 3.9910. Min Range: -3.9910

Max Act: 3.7091. Min Act: -0.1700

Data Index: 7631626 (Open Web Text)

Max Activating Token Index: 960

Text #14

Max Range: 3.9910. Min Range: -3.9910

Max Act: 3.6937. Min Act: -0.1700

Data Index: 6850794 (Open Web Text)

Max Activating Token Index: 645

Text #15

Max Range: 3.9910. Min Range: -3.9910

Max Act: 3.7015. Min Act: -0.1700

Data Index: 6513518 (Open Web Text)

Max Activating Token Index: 313

Text #16

Max Range: 3.9910. Min Range: -3.9910

Max Act: 3.6929. Min Act: -0.1700

Data Index: 7730176 (Open Web Text)

Max Activating Token Index: 580

Text #17

Max Range: 3.9910. Min Range: -3.9910

Max Act: 3.7065. Min Act: -0.1700

Data Index: 205712 (Open Web Text)

Max Activating Token Index: 994

Text #18

Max Range: 3.9910. Min Range: -3.9910

Max Act: 3.7220. Min Act: -0.1700

Data Index: 2389345 (Open Web Text)

Max Activating Token Index: 574

Text #19

Max Range: 3.9910. Min Range: -3.9910

Max Act: 3.6644. Min Act: -0.1700

Data Index: 5695249 (Open Web Text)

Max Activating Token Index: 837