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

Dataset: Open Web Text

Neuron 1587 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: 1.6041. Min Range: -1.6041

Max Act: 1.6041. Min Act: -0.1636

Data Index: 286012 (Open Web Text)

Max Activating Token Index: 492

Text #1

Max Range: 1.6041. Min Range: -1.6041

Max Act: 1.5868. Min Act: -0.1683

Data Index: 1287398 (Open Web Text)

Max Activating Token Index: 951

Text #2

Max Range: 1.6041. Min Range: -1.6041

Max Act: 1.5772. Min Act: -0.1698

Data Index: 286011 (Open Web Text)

Max Activating Token Index: 922

Text #3

Max Range: 1.6041. Min Range: -1.6041

Max Act: 1.5538. Min Act: -0.1532

Data Index: 8352796 (Open Web Text)

Max Activating Token Index: 395

Text #4

Max Range: 1.6041. Min Range: -1.6041

Max Act: 1.5416. Min Act: -0.1665

Data Index: 7066833 (Open Web Text)

Max Activating Token Index: 356

Text #5

Max Range: 1.6041. Min Range: -1.6041

Max Act: 1.5483. Min Act: -0.1621

Data Index: 3065897 (Open Web Text)

Max Activating Token Index: 928

Text #6

Max Range: 1.6041. Min Range: -1.6041

Max Act: 1.5466. Min Act: -0.1700

Data Index: 5304701 (Open Web Text)

Max Activating Token Index: 354

Text #7

Max Range: 1.6041. Min Range: -1.6041

Max Act: 1.5358. Min Act: -0.1700

Data Index: 7562564 (Open Web Text)

Max Activating Token Index: 483

Text #8

Max Range: 1.6041. Min Range: -1.6041

Max Act: 1.5429. Min Act: -0.1592

Data Index: 959584 (Open Web Text)

Max Activating Token Index: 818

Text #9

Max Range: 1.6041. Min Range: -1.6041

Max Act: 1.5294. Min Act: -0.1516

Data Index: 1400072 (Open Web Text)

Max Activating Token Index: 332

Text #10

Max Range: 1.6041. Min Range: -1.6041

Max Act: 1.5278. Min Act: -0.1699

Data Index: 286014 (Open Web Text)

Max Activating Token Index: 266

Text #11

Max Range: 1.6041. Min Range: -1.6041

Max Act: 1.5366. Min Act: -0.1649

Data Index: 211528 (Open Web Text)

Max Activating Token Index: 967

Text #12

Max Range: 1.6041. Min Range: -1.6041

Max Act: 1.5208. Min Act: -0.1693

Data Index: 74873 (Open Web Text)

Max Activating Token Index: 970

Text #13

Max Range: 1.6041. Min Range: -1.6041

Max Act: 1.5156. Min Act: -0.1648

Data Index: 6763790 (Open Web Text)

Max Activating Token Index: 513

Text #14

Max Range: 1.6041. Min Range: -1.6041

Max Act: 1.5205. Min Act: -0.1685

Data Index: 1559170 (Open Web Text)

Max Activating Token Index: 405

Text #15

Max Range: 1.6041. Min Range: -1.6041

Max Act: 1.5241. Min Act: -0.1516

Data Index: 3320411 (Open Web Text)

Max Activating Token Index: 710

Text #16

Max Range: 1.6041. Min Range: -1.6041

Max Act: 1.5180. Min Act: -0.1693

Data Index: 4685886 (Open Web Text)

Max Activating Token Index: 94

Text #17

Max Range: 1.6041. Min Range: -1.6041

Max Act: 1.5255. Min Act: -0.1696

Data Index: 3904363 (Open Web Text)

Max Activating Token Index: 285

Text #18

Max Range: 1.6041. Min Range: -1.6041

Max Act: 1.5209. Min Act: -0.1516

Data Index: 1766304 (Open Web Text)

Max Activating Token Index: 258

Text #19

Max Range: 1.6041. Min Range: -1.6041

Max Act: 1.5155. Min Act: -0.1516

Data Index: 2202366 (Open Web Text)

Max Activating Token Index: 532