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

Dataset: Open Web Text

Neuron 2727 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: 3.7731. Min Range: -3.7731

Max Act: 3.7731. Min Act: -0.1700

Data Index: 6630221 (Open Web Text)

Max Activating Token Index: 552

Text #1

Max Range: 3.7731. Min Range: -3.7731

Max Act: 3.7605. Min Act: -0.1700

Data Index: 7432389 (Open Web Text)

Max Activating Token Index: 645

Text #2

Max Range: 3.7731. Min Range: -3.7731

Max Act: 3.7485. Min Act: -0.1700

Data Index: 3428887 (Open Web Text)

Max Activating Token Index: 983

Text #3

Max Range: 3.7731. Min Range: -3.7731

Max Act: 3.7303. Min Act: -0.1700

Data Index: 8467038 (Open Web Text)

Max Activating Token Index: 586

Text #4

Max Range: 3.7731. Min Range: -3.7731

Max Act: 3.7579. Min Act: -0.1700

Data Index: 1894574 (Open Web Text)

Max Activating Token Index: 822

Text #5

Max Range: 3.7731. Min Range: -3.7731

Max Act: 3.6919. Min Act: -0.1700

Data Index: 7694170 (Open Web Text)

Max Activating Token Index: 492

Text #6

Max Range: 3.7731. Min Range: -3.7731

Max Act: 3.7455. Min Act: -0.1700

Data Index: 3445920 (Open Web Text)

Max Activating Token Index: 358

Text #7

Max Range: 3.7731. Min Range: -3.7731

Max Act: 3.7026. Min Act: -0.1700

Data Index: 2238329 (Open Web Text)

Max Activating Token Index: 548

Text #8

Max Range: 3.7731. Min Range: -3.7731

Max Act: 3.6767. Min Act: -0.1700

Data Index: 7756412 (Open Web Text)

Max Activating Token Index: 253

Text #9

Max Range: 3.7731. Min Range: -3.7731

Max Act: 3.6693. Min Act: -0.1700

Data Index: 1103246 (Open Web Text)

Max Activating Token Index: 652

Text #10

Max Range: 3.7731. Min Range: -3.7731

Max Act: 3.6733. Min Act: -0.1700

Data Index: 8803307 (Open Web Text)

Max Activating Token Index: 909

Text #11

Max Range: 3.7731. Min Range: -3.7731

Max Act: 3.6474. Min Act: -0.1700

Data Index: 5953570 (Open Web Text)

Max Activating Token Index: 680

Text #12

Max Range: 3.7731. Min Range: -3.7731

Max Act: 3.6379. Min Act: -0.1700

Data Index: 299888 (Open Web Text)

Max Activating Token Index: 429

Text #13

Max Range: 3.7731. Min Range: -3.7731

Max Act: 3.6133. Min Act: -0.1700

Data Index: 8647315 (Open Web Text)

Max Activating Token Index: 625

Text #14

Max Range: 3.7731. Min Range: -3.7731

Max Act: 3.6345. Min Act: -0.1700

Data Index: 5957817 (Open Web Text)

Max Activating Token Index: 989

Text #15

Max Range: 3.7731. Min Range: -3.7731

Max Act: 3.6048. Min Act: -0.1700

Data Index: 2649199 (Open Web Text)

Max Activating Token Index: 404

Text #16

Max Range: 3.7731. Min Range: -3.7731

Max Act: 3.6057. Min Act: -0.1700

Data Index: 3428888 (Open Web Text)

Max Activating Token Index: 58

Text #17

Max Range: 3.7731. Min Range: -3.7731

Max Act: 3.6329. Min Act: -0.1700

Data Index: 6704290 (Open Web Text)

Max Activating Token Index: 540

Text #18

Max Range: 3.7731. Min Range: -3.7731

Max Act: 3.6207. Min Act: -0.1700

Data Index: 2349643 (Open Web Text)

Max Activating Token Index: 765

Text #19

Max Range: 3.7731. Min Range: -3.7731

Max Act: 3.5904. Min Act: -0.1700

Data Index: 6270581 (Open Web Text)

Max Activating Token Index: 884