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

Dataset: Open Web Text

Neuron 32 in Layer 1

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: 5.1725. Min Range: -5.1725

Max Act: 5.1725. Min Act: -0.1700

Data Index: 6781483 (Open Web Text)

Max Activating Token Index: 115

Text #1

Max Range: 5.1725. Min Range: -5.1725

Max Act: 5.0246. Min Act: -0.1694

Data Index: 8687173 (Open Web Text)

Max Activating Token Index: 97

Text #2

Max Range: 5.1725. Min Range: -5.1725

Max Act: 4.8813. Min Act: -0.1700

Data Index: 7955473 (Open Web Text)

Max Activating Token Index: 40

Text #3

Max Range: 5.1725. Min Range: -5.1725

Max Act: 4.8742. Min Act: -0.1700

Data Index: 5720110 (Open Web Text)

Max Activating Token Index: 630

Text #4

Max Range: 5.1725. Min Range: -5.1725

Max Act: 4.8417. Min Act: -0.1700

Data Index: 752856 (Open Web Text)

Max Activating Token Index: 43

Text #5

Max Range: 5.1725. Min Range: -5.1725

Max Act: 4.8011. Min Act: -0.1700

Data Index: 7856288 (Open Web Text)

Max Activating Token Index: 58

Text #6

Max Range: 5.1725. Min Range: -5.1725

Max Act: 4.7523. Min Act: -0.1692

Data Index: 5689152 (Open Web Text)

Max Activating Token Index: 40

Text #7

Max Range: 5.1725. Min Range: -5.1725

Max Act: 4.7455. Min Act: -0.1698

Data Index: 5507279 (Open Web Text)

Max Activating Token Index: 74

Text #8

Max Range: 5.1725. Min Range: -5.1725

Max Act: 4.7543. Min Act: -0.1692

Data Index: 5293559 (Open Web Text)

Max Activating Token Index: 834

Text #9

Max Range: 5.1725. Min Range: -5.1725

Max Act: 4.7120. Min Act: -0.1639

Data Index: 5817021 (Open Web Text)

Max Activating Token Index: 56

Text #10

Max Range: 5.1725. Min Range: -5.1725

Max Act: 4.7148. Min Act: -0.1700

Data Index: 3846849 (Open Web Text)

Max Activating Token Index: 58

Text #11

Max Range: 5.1725. Min Range: -5.1725

Max Act: 4.6674. Min Act: -0.1700

Data Index: 1992609 (Open Web Text)

Max Activating Token Index: 90

Text #12

Max Range: 5.1725. Min Range: -5.1725

Max Act: 4.6859. Min Act: -0.1692

Data Index: 6258678 (Open Web Text)

Max Activating Token Index: 190

Text #13

Max Range: 5.1725. Min Range: -5.1725

Max Act: 4.6419. Min Act: -0.1695

Data Index: 1604206 (Open Web Text)

Max Activating Token Index: 359

Text #14

Max Range: 5.1725. Min Range: -5.1725

Max Act: 4.6540. Min Act: -0.1700

Data Index: 6612969 (Open Web Text)

Max Activating Token Index: 261

Text #15

Max Range: 5.1725. Min Range: -5.1725

Max Act: 4.6693. Min Act: -0.1700

Data Index: 8397016 (Open Web Text)

Max Activating Token Index: 72

Text #16

Max Range: 5.1725. Min Range: -5.1725

Max Act: 4.6780. Min Act: -0.1698

Data Index: 5191989 (Open Web Text)

Max Activating Token Index: 80

Text #17

Max Range: 5.1725. Min Range: -5.1725

Max Act: 4.6231. Min Act: -0.1700

Data Index: 150790 (Open Web Text)

Max Activating Token Index: 173

Text #18

Max Range: 5.1725. Min Range: -5.1725

Max Act: 4.6561. Min Act: -0.1700

Data Index: 918857 (Open Web Text)

Max Activating Token Index: 600

Text #19

Max Range: 5.1725. Min Range: -5.1725

Max Act: 4.6425. Min Act: -0.1700

Data Index: 1914465 (Open Web Text)

Max Activating Token Index: 64