Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5952 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.4182. Min Range: -0.4182

Max Act: 0.4182. Min Act: -0.0000

Data Index: 660628 (C4 (Web Text))

Max Activating Token Index: 93

Text #1

Max Range: 0.4182. Min Range: -0.4182

Max Act: 0.2563. Min Act: -0.0000

Data Index: 628997 (C4 (Web Text))

Max Activating Token Index: 849

Text #2

Max Range: 0.4182. Min Range: -0.4182

Max Act: 0.2436. Min Act: -0.0000

Data Index: 1280782 (C4 (Web Text))

Max Activating Token Index: 714

Text #3

Max Range: 0.4182. Min Range: -0.4182

Max Act: 0.2415. Min Act: -0.0000

Data Index: 629630 (C4 (Web Text))

Max Activating Token Index: 156

Text #4

Max Range: 0.4182. Min Range: -0.4182

Max Act: 0.2231. Min Act: -0.0000

Data Index: 1141081 (C4 (Web Text))

Max Activating Token Index: 244

Text #5

Max Range: 0.4182. Min Range: -0.4182

Max Act: 0.2293. Min Act: -0.0000

Data Index: 152486 (C4 (Web Text))

Max Activating Token Index: 802

Text #6

Max Range: 0.4182. Min Range: -0.4182

Max Act: 0.2352. Min Act: -0.0000

Data Index: 126928 (C4 (Web Text))

Max Activating Token Index: 912

Text #7

Max Range: 0.4182. Min Range: -0.4182

Max Act: 0.2293. Min Act: -0.0000

Data Index: 1150372 (C4 (Web Text))

Max Activating Token Index: 805

Text #8

Max Range: 0.4182. Min Range: -0.4182

Max Act: 0.2357. Min Act: -0.0000

Data Index: 1030440 (C4 (Web Text))

Max Activating Token Index: 443

Text #9

Max Range: 0.4182. Min Range: -0.4182

Max Act: 0.2248. Min Act: -0.0000

Data Index: 854030 (C4 (Web Text))

Max Activating Token Index: 563

Text #10

Max Range: 0.4182. Min Range: -0.4182

Max Act: 0.2157. Min Act: -0.0000

Data Index: 277634 (C4 (Web Text))

Max Activating Token Index: 499

Text #11

Max Range: 0.4182. Min Range: -0.4182

Max Act: 0.2230. Min Act: -0.0000

Data Index: 1283877 (C4 (Web Text))

Max Activating Token Index: 791

Text #12

Max Range: 0.4182. Min Range: -0.4182

Max Act: 0.2109. Min Act: -0.0000

Data Index: 900895 (C4 (Web Text))

Max Activating Token Index: 88

Text #13

Max Range: 0.4182. Min Range: -0.4182

Max Act: 0.2254. Min Act: -0.0000

Data Index: 481512 (C4 (Web Text))

Max Activating Token Index: 985

Text #14

Max Range: 0.4182. Min Range: -0.4182

Max Act: 0.2305. Min Act: -0.0000

Data Index: 454458 (C4 (Web Text))

Max Activating Token Index: 695

Text #15

Max Range: 0.4182. Min Range: -0.4182

Max Act: 0.2284. Min Act: -0.0000

Data Index: 374432 (C4 (Web Text))

Max Activating Token Index: 240

Text #16

Max Range: 0.4182. Min Range: -0.4182

Max Act: 0.1952. Min Act: -0.0000

Data Index: 291316 (C4 (Web Text))

Max Activating Token Index: 851

Text #17

Max Range: 0.4182. Min Range: -0.4182

Max Act: 0.2235. Min Act: -0.0000

Data Index: 251655 (C4 (Web Text))

Max Activating Token Index: 988

Text #18

Max Range: 0.4182. Min Range: -0.4182

Max Act: 0.2107. Min Act: -0.0000

Data Index: 1350462 (C4 (Web Text))

Max Activating Token Index: 771

Text #19

Max Range: 0.4182. Min Range: -0.4182

Max Act: 0.2223. Min Act: -0.0000

Data Index: 138500 (C4 (Web Text))

Max Activating Token Index: 539