Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 3523 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1411. Min Range: -0.1411

Max Act: 0.1411. Min Act: -0.0000

Data Index: 552832 (C4 (Web Text))

Max Activating Token Index: 670

Text #1

Max Range: 0.1411. Min Range: -0.1411

Max Act: 0.1365. Min Act: -0.0000

Data Index: 462536 (C4 (Web Text))

Max Activating Token Index: 583

Text #2

Max Range: 0.1411. Min Range: -0.1411

Max Act: 0.1296. Min Act: -0.0000

Data Index: 1189458 (C4 (Web Text))

Max Activating Token Index: 289

Text #3

Max Range: 0.1411. Min Range: -0.1411

Max Act: 0.1239. Min Act: -0.0000

Data Index: 58918 (C4 (Web Text))

Max Activating Token Index: 872

Text #4

Max Range: 0.1411. Min Range: -0.1411

Max Act: 0.1272. Min Act: -0.0000

Data Index: 407176 (C4 (Web Text))

Max Activating Token Index: 917

Text #5

Max Range: 0.1411. Min Range: -0.1411

Max Act: 0.1267. Min Act: -0.0000

Data Index: 436215 (C4 (Web Text))

Max Activating Token Index: 15

Text #6

Max Range: 0.1411. Min Range: -0.1411

Max Act: 0.1260. Min Act: -0.0001

Data Index: 1332786 (C4 (Web Text))

Max Activating Token Index: 677

Text #7

Max Range: 0.1411. Min Range: -0.1411

Max Act: 0.1299. Min Act: -0.0000

Data Index: 1140311 (C4 (Web Text))

Max Activating Token Index: 945

Text #8

Max Range: 0.1411. Min Range: -0.1411

Max Act: 0.1206. Min Act: -0.0000

Data Index: 310086 (C4 (Web Text))

Max Activating Token Index: 812

Text #9

Max Range: 0.1411. Min Range: -0.1411

Max Act: 0.1210. Min Act: -0.0000

Data Index: 677790 (C4 (Web Text))

Max Activating Token Index: 842

Text #10

Max Range: 0.1411. Min Range: -0.1411

Max Act: 0.1150. Min Act: -0.0001

Data Index: 146988 (C4 (Web Text))

Max Activating Token Index: 1014

Text #11

Max Range: 0.1411. Min Range: -0.1411

Max Act: 0.1192. Min Act: -0.0000

Data Index: 49844 (C4 (Web Text))

Max Activating Token Index: 567

Text #12

Max Range: 0.1411. Min Range: -0.1411

Max Act: 0.1182. Min Act: -0.0000

Data Index: 897425 (C4 (Web Text))

Max Activating Token Index: 634

Text #13

Max Range: 0.1411. Min Range: -0.1411

Max Act: 0.1185. Min Act: -0.0000

Data Index: 531360 (C4 (Web Text))

Max Activating Token Index: 378

Text #14

Max Range: 0.1411. Min Range: -0.1411

Max Act: 0.1171. Min Act: -0.0000

Data Index: 225130 (C4 (Web Text))

Max Activating Token Index: 333

Text #15

Max Range: 0.1411. Min Range: -0.1411

Max Act: 0.1162. Min Act: -0.0000

Data Index: 754713 (C4 (Web Text))

Max Activating Token Index: 235

Text #16

Max Range: 0.1411. Min Range: -0.1411

Max Act: 0.1116. Min Act: -0.0000

Data Index: 836461 (C4 (Web Text))

Max Activating Token Index: 355

Text #17

Max Range: 0.1411. Min Range: -0.1411

Max Act: 0.1151. Min Act: -0.0000

Data Index: 196773 (C4 (Web Text))

Max Activating Token Index: 489

Text #18

Max Range: 0.1411. Min Range: -0.1411

Max Act: 0.1102. Min Act: -0.0000

Data Index: 235865 (C4 (Web Text))

Max Activating Token Index: 435

Text #19

Max Range: 0.1411. Min Range: -0.1411

Max Act: 0.1104. Min Act: -0.0000

Data Index: 158077 (C4 (Web Text))

Max Activating Token Index: 783