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

Dataset: Open Web Text

Neuron 2630 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: 3.1262. Min Range: -3.1262

Max Act: 3.1262. Min Act: -0.1700

Data Index: 4458280 (Open Web Text)

Max Activating Token Index: 672

Text #1

Max Range: 3.1262. Min Range: -3.1262

Max Act: 3.1046. Min Act: -0.1700

Data Index: 322313 (Open Web Text)

Max Activating Token Index: 326

Text #2

Max Range: 3.1262. Min Range: -3.1262

Max Act: 3.1003. Min Act: -0.1700

Data Index: 8242845 (Open Web Text)

Max Activating Token Index: 632

Text #3

Max Range: 3.1262. Min Range: -3.1262

Max Act: 3.0886. Min Act: -0.1700

Data Index: 8588679 (Open Web Text)

Max Activating Token Index: 880

Text #4

Max Range: 3.1262. Min Range: -3.1262

Max Act: 3.0509. Min Act: -0.1700

Data Index: 2830153 (Open Web Text)

Max Activating Token Index: 29

Text #5

Max Range: 3.1262. Min Range: -3.1262

Max Act: 3.0579. Min Act: -0.1700

Data Index: 3390019 (Open Web Text)

Max Activating Token Index: 649

Text #6

Max Range: 3.1262. Min Range: -3.1262

Max Act: 3.0468. Min Act: -0.1700

Data Index: 8241243 (Open Web Text)

Max Activating Token Index: 680

Text #7

Max Range: 3.1262. Min Range: -3.1262

Max Act: 3.0504. Min Act: -0.1700

Data Index: 1526148 (Open Web Text)

Max Activating Token Index: 610

Text #8

Max Range: 3.1262. Min Range: -3.1262

Max Act: 3.0677. Min Act: -0.1700

Data Index: 7029790 (Open Web Text)

Max Activating Token Index: 447

Text #9

Max Range: 3.1262. Min Range: -3.1262

Max Act: 3.0546. Min Act: -0.1700

Data Index: 6825442 (Open Web Text)

Max Activating Token Index: 948

Text #10

Max Range: 3.1262. Min Range: -3.1262

Max Act: 3.0432. Min Act: -0.1700

Data Index: 7703913 (Open Web Text)

Max Activating Token Index: 435

Text #11

Max Range: 3.1262. Min Range: -3.1262

Max Act: 3.0607. Min Act: -0.1700

Data Index: 7462979 (Open Web Text)

Max Activating Token Index: 464

Text #12

Max Range: 3.1262. Min Range: -3.1262

Max Act: 3.0586. Min Act: -0.1700

Data Index: 7239863 (Open Web Text)

Max Activating Token Index: 567

Text #13

Max Range: 3.1262. Min Range: -3.1262

Max Act: 3.0520. Min Act: -0.1700

Data Index: 1211852 (Open Web Text)

Max Activating Token Index: 566

Text #14

Max Range: 3.1262. Min Range: -3.1262

Max Act: 3.0489. Min Act: -0.1700

Data Index: 4056954 (Open Web Text)

Max Activating Token Index: 127

Text #15

Max Range: 3.1262. Min Range: -3.1262

Max Act: 3.0443. Min Act: -0.1700

Data Index: 5423685 (Open Web Text)

Max Activating Token Index: 591

Text #16

Max Range: 3.1262. Min Range: -3.1262

Max Act: 3.0333. Min Act: -0.1700

Data Index: 3472168 (Open Web Text)

Max Activating Token Index: 223

Text #17

Max Range: 3.1262. Min Range: -3.1262

Max Act: 3.0415. Min Act: -0.1700

Data Index: 4602853 (Open Web Text)

Max Activating Token Index: 22

Text #18

Max Range: 3.1262. Min Range: -3.1262

Max Act: 3.0393. Min Act: -0.1700

Data Index: 3453570 (Open Web Text)

Max Activating Token Index: 163

Text #19

Max Range: 3.1262. Min Range: -3.1262

Max Act: 3.0315. Min Act: -0.1700

Data Index: 3341485 (Open Web Text)

Max Activating Token Index: 586