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

Dataset: Open Web Text

Neuron 1755 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: 3.9542. Min Range: -3.9542

Max Act: 3.9453. Min Act: -0.1700

Data Index: 7516453 (Open Web Text)

Max Activating Token Index: 729

Text #1

Max Range: 3.9542. Min Range: -3.9542

Max Act: 3.9242. Min Act: -0.1700

Data Index: 3259668 (Open Web Text)

Max Activating Token Index: 501

Text #2

Max Range: 3.9542. Min Range: -3.9542

Max Act: 3.9542. Min Act: -0.1700

Data Index: 4025894 (Open Web Text)

Max Activating Token Index: 447

Text #3

Max Range: 3.9542. Min Range: -3.9542

Max Act: 3.9392. Min Act: -0.1700

Data Index: 6222859 (Open Web Text)

Max Activating Token Index: 131

Text #4

Max Range: 3.9542. Min Range: -3.9542

Max Act: 3.9037. Min Act: -0.1700

Data Index: 6109526 (Open Web Text)

Max Activating Token Index: 783

Text #5

Max Range: 3.9542. Min Range: -3.9542

Max Act: 3.8792. Min Act: -0.1700

Data Index: 6052612 (Open Web Text)

Max Activating Token Index: 710

Text #6

Max Range: 3.9542. Min Range: -3.9542

Max Act: 3.8735. Min Act: -0.1700

Data Index: 4689286 (Open Web Text)

Max Activating Token Index: 206

Text #7

Max Range: 3.9542. Min Range: -3.9542

Max Act: 3.8905. Min Act: -0.1700

Data Index: 2607290 (Open Web Text)

Max Activating Token Index: 287

Text #8

Max Range: 3.9542. Min Range: -3.9542

Max Act: 3.8958. Min Act: -0.1700

Data Index: 6984752 (Open Web Text)

Max Activating Token Index: 609

Text #9

Max Range: 3.9542. Min Range: -3.9542

Max Act: 3.9075. Min Act: -0.1700

Data Index: 435330 (Open Web Text)

Max Activating Token Index: 899

Text #10

Max Range: 3.9542. Min Range: -3.9542

Max Act: 3.8631. Min Act: -0.1700

Data Index: 7935867 (Open Web Text)

Max Activating Token Index: 339

Text #11

Max Range: 3.9542. Min Range: -3.9542

Max Act: 3.8765. Min Act: -0.1700

Data Index: 2824414 (Open Web Text)

Max Activating Token Index: 183

Text #12

Max Range: 3.9542. Min Range: -3.9542

Max Act: 3.8663. Min Act: -0.1700

Data Index: 6304150 (Open Web Text)

Max Activating Token Index: 75

Text #13

Max Range: 3.9542. Min Range: -3.9542

Max Act: 3.8469. Min Act: -0.1700

Data Index: 6770973 (Open Web Text)

Max Activating Token Index: 725

Text #14

Max Range: 3.9542. Min Range: -3.9542

Max Act: 3.8270. Min Act: -0.1700

Data Index: 2607166 (Open Web Text)

Max Activating Token Index: 441

Text #15

Max Range: 3.9542. Min Range: -3.9542

Max Act: 3.8450. Min Act: -0.1700

Data Index: 667159 (Open Web Text)

Max Activating Token Index: 471

Text #16

Max Range: 3.9542. Min Range: -3.9542

Max Act: 3.8649. Min Act: -0.1700

Data Index: 1034459 (Open Web Text)

Max Activating Token Index: 891

Text #17

Max Range: 3.9542. Min Range: -3.9542

Max Act: 3.8339. Min Act: -0.1700

Data Index: 164582 (Open Web Text)

Max Activating Token Index: 302

Text #18

Max Range: 3.9542. Min Range: -3.9542

Max Act: 3.8293. Min Act: -0.1700

Data Index: 7118517 (Open Web Text)

Max Activating Token Index: 607

Text #19

Max Range: 3.9542. Min Range: -3.9542

Max Act: 3.8468. Min Act: -0.1700

Data Index: 4345170 (Open Web Text)

Max Activating Token Index: 959