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

Dataset: Open Web Text

Neuron 1242 in Layer 0

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: 1.6714. Min Range: -1.6714

Max Act: 1.6714. Min Act: -0.1609

Data Index: 1091854 (Open Web Text)

Max Activating Token Index: 448

Text #1

Max Range: 1.6714. Min Range: -1.6714

Max Act: 1.6589. Min Act: -0.1506

Data Index: 8184846 (Open Web Text)

Max Activating Token Index: 55

Text #2

Max Range: 1.6714. Min Range: -1.6714

Max Act: 1.6435. Min Act: -0.1691

Data Index: 708775 (Open Web Text)

Max Activating Token Index: 431

Text #3

Max Range: 1.6714. Min Range: -1.6714

Max Act: 1.6229. Min Act: -0.1430

Data Index: 1821588 (Open Web Text)

Max Activating Token Index: 367

Text #4

Max Range: 1.6714. Min Range: -1.6714

Max Act: 1.6369. Min Act: -0.1699

Data Index: 8484449 (Open Web Text)

Max Activating Token Index: 20

Text #5

Max Range: 1.6714. Min Range: -1.6714

Max Act: 1.6311. Min Act: -0.1692

Data Index: 7731406 (Open Web Text)

Max Activating Token Index: 46

Text #6

Max Range: 1.6714. Min Range: -1.6714

Max Act: 1.6345. Min Act: -0.1688

Data Index: 6425159 (Open Web Text)

Max Activating Token Index: 59

Text #7

Max Range: 1.6714. Min Range: -1.6714

Max Act: 1.6280. Min Act: -0.1700

Data Index: 4152503 (Open Web Text)

Max Activating Token Index: 612

Text #8

Max Range: 1.6714. Min Range: -1.6714

Max Act: 1.6225. Min Act: -0.1700

Data Index: 6060690 (Open Web Text)

Max Activating Token Index: 73

Text #9

Max Range: 1.6714. Min Range: -1.6714

Max Act: 1.6176. Min Act: -0.1683

Data Index: 858243 (Open Web Text)

Max Activating Token Index: 493

Text #10

Max Range: 1.6714. Min Range: -1.6714

Max Act: 1.6151. Min Act: -0.1589

Data Index: 2666095 (Open Web Text)

Max Activating Token Index: 409

Text #11

Max Range: 1.6714. Min Range: -1.6714

Max Act: 1.6100. Min Act: -0.1694

Data Index: 4415854 (Open Web Text)

Max Activating Token Index: 456

Text #12

Max Range: 1.6714. Min Range: -1.6714

Max Act: 1.6135. Min Act: -0.1629

Data Index: 596184 (Open Web Text)

Max Activating Token Index: 360

Text #13

Max Range: 1.6714. Min Range: -1.6714

Max Act: 1.6144. Min Act: -0.1689

Data Index: 126052 (Open Web Text)

Max Activating Token Index: 589

Text #14

Max Range: 1.6714. Min Range: -1.6714

Max Act: 1.6225. Min Act: -0.1497

Data Index: 7136435 (Open Web Text)

Max Activating Token Index: 627

Text #15

Max Range: 1.6714. Min Range: -1.6714

Max Act: 1.6127. Min Act: -0.1686

Data Index: 5721839 (Open Web Text)

Max Activating Token Index: 406

Text #16

Max Range: 1.6714. Min Range: -1.6714

Max Act: 1.6002. Min Act: -0.1698

Data Index: 3243690 (Open Web Text)

Max Activating Token Index: 367

Text #17

Max Range: 1.6714. Min Range: -1.6714

Max Act: 1.6003. Min Act: -0.1694

Data Index: 1293357 (Open Web Text)

Max Activating Token Index: 693

Text #18

Max Range: 1.6714. Min Range: -1.6714

Max Act: 1.6033. Min Act: -0.1625

Data Index: 5794867 (Open Web Text)

Max Activating Token Index: 394

Text #19

Max Range: 1.6714. Min Range: -1.6714

Max Act: 1.6066. Min Act: -0.1698

Data Index: 5705549 (Open Web Text)

Max Activating Token Index: 386