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

Dataset: Open Web Text

Neuron 461 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: 1.6325. Min Range: -1.6325

Max Act: 1.6325. Min Act: -0.1688

Data Index: 2450068 (Open Web Text)

Max Activating Token Index: 18

Text #1

Max Range: 1.6325. Min Range: -1.6325

Max Act: 1.6228. Min Act: -0.1699

Data Index: 5474131 (Open Web Text)

Max Activating Token Index: 535

Text #2

Max Range: 1.6325. Min Range: -1.6325

Max Act: 1.6085. Min Act: -0.1688

Data Index: 1352400 (Open Web Text)

Max Activating Token Index: 719

Text #3

Max Range: 1.6325. Min Range: -1.6325

Max Act: 1.5734. Min Act: -0.1688

Data Index: 7944987 (Open Web Text)

Max Activating Token Index: 272

Text #4

Max Range: 1.6325. Min Range: -1.6325

Max Act: 1.5527. Min Act: -0.1688

Data Index: 2680220 (Open Web Text)

Max Activating Token Index: 532

Text #5

Max Range: 1.6325. Min Range: -1.6325

Max Act: 1.5657. Min Act: -0.1692

Data Index: 814870 (Open Web Text)

Max Activating Token Index: 861

Text #6

Max Range: 1.6325. Min Range: -1.6325

Max Act: 1.5618. Min Act: -0.1692

Data Index: 3498293 (Open Web Text)

Max Activating Token Index: 688

Text #7

Max Range: 1.6325. Min Range: -1.6325

Max Act: 1.5586. Min Act: -0.1692

Data Index: 4947156 (Open Web Text)

Max Activating Token Index: 654

Text #8

Max Range: 1.6325. Min Range: -1.6325

Max Act: 1.5507. Min Act: -0.1698

Data Index: 6782748 (Open Web Text)

Max Activating Token Index: 40

Text #9

Max Range: 1.6325. Min Range: -1.6325

Max Act: 1.5591. Min Act: -0.1688

Data Index: 2460248 (Open Web Text)

Max Activating Token Index: 713

Text #10

Max Range: 1.6325. Min Range: -1.6325

Max Act: 1.5379. Min Act: -0.1697

Data Index: 1594009 (Open Web Text)

Max Activating Token Index: 882

Text #11

Max Range: 1.6325. Min Range: -1.6325

Max Act: 1.5399. Min Act: -0.1688

Data Index: 4835427 (Open Web Text)

Max Activating Token Index: 766

Text #12

Max Range: 1.6325. Min Range: -1.6325

Max Act: 1.5485. Min Act: -0.1700

Data Index: 626577 (Open Web Text)

Max Activating Token Index: 797

Text #13

Max Range: 1.6325. Min Range: -1.6325

Max Act: 1.5313. Min Act: -0.1688

Data Index: 2422472 (Open Web Text)

Max Activating Token Index: 941

Text #14

Max Range: 1.6325. Min Range: -1.6325

Max Act: 1.5373. Min Act: -0.1690

Data Index: 5109508 (Open Web Text)

Max Activating Token Index: 839

Text #15

Max Range: 1.6325. Min Range: -1.6325

Max Act: 1.5316. Min Act: -0.1699

Data Index: 1215579 (Open Web Text)

Max Activating Token Index: 888

Text #16

Max Range: 1.6325. Min Range: -1.6325

Max Act: 1.5220. Min Act: -0.1700

Data Index: 5394976 (Open Web Text)

Max Activating Token Index: 341

Text #17

Max Range: 1.6325. Min Range: -1.6325

Max Act: 1.5172. Min Act: -0.1690

Data Index: 6609701 (Open Web Text)

Max Activating Token Index: 521

Text #18

Max Range: 1.6325. Min Range: -1.6325

Max Act: 1.5310. Min Act: -0.1692

Data Index: 4275056 (Open Web Text)

Max Activating Token Index: 152

Text #19

Max Range: 1.6325. Min Range: -1.6325

Max Act: 1.5178. Min Act: -0.1688

Data Index: 6149275 (Open Web Text)

Max Activating Token Index: 100