Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 200 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.4264. Min Range: -1.4264

Max Act: 1.4264. Min Act: -0.0000

Data Index: 236936 (C4 (Web Text))

Max Activating Token Index: 401

Text #1

Max Range: 1.4264. Min Range: -1.4264

Max Act: 1.3339. Min Act: -0.0000

Data Index: 166979 (C4 (Web Text))

Max Activating Token Index: 290

Text #2

Max Range: 1.4264. Min Range: -1.4264

Max Act: 1.2208. Min Act: -0.0000

Data Index: 639410 (C4 (Web Text))

Max Activating Token Index: 774

Text #3

Max Range: 1.4264. Min Range: -1.4264

Max Act: 1.2264. Min Act: -0.0000

Data Index: 540766 (C4 (Web Text))

Max Activating Token Index: 553

Text #4

Max Range: 1.4264. Min Range: -1.4264

Max Act: 1.3044. Min Act: -0.0000

Data Index: 983891 (C4 (Web Text))

Max Activating Token Index: 491

Text #5

Max Range: 1.4264. Min Range: -1.4264

Max Act: 1.2352. Min Act: -0.0000

Data Index: 596732 (C4 (Web Text))

Max Activating Token Index: 375

Text #6

Max Range: 1.4264. Min Range: -1.4264

Max Act: 1.2025. Min Act: -0.0000

Data Index: 324174 (C4 (Web Text))

Max Activating Token Index: 258

Text #7

Max Range: 1.4264. Min Range: -1.4264

Max Act: 1.2357. Min Act: -0.0000

Data Index: 631915 (C4 (Web Text))

Max Activating Token Index: 345

Text #8

Max Range: 1.4264. Min Range: -1.4264

Max Act: 1.2248. Min Act: -0.0000

Data Index: 244105 (C4 (Web Text))

Max Activating Token Index: 700

Text #9

Max Range: 1.4264. Min Range: -1.4264

Max Act: 1.2163. Min Act: -0.0000

Data Index: 1323759 (C4 (Web Text))

Max Activating Token Index: 240

Text #10

Max Range: 1.4264. Min Range: -1.4264

Max Act: 1.1789. Min Act: -0.0000

Data Index: 477029 (C4 (Web Text))

Max Activating Token Index: 382

Text #11

Max Range: 1.4264. Min Range: -1.4264

Max Act: 1.1436. Min Act: -0.0000

Data Index: 903577 (C4 (Web Text))

Max Activating Token Index: 930

Text #12

Max Range: 1.4264. Min Range: -1.4264

Max Act: 1.1720. Min Act: -0.0000

Data Index: 884205 (C4 (Web Text))

Max Activating Token Index: 955

Text #13

Max Range: 1.4264. Min Range: -1.4264

Max Act: 0.5705. Min Act: -0.0000

Data Index: 486329 (C4 (Web Text))

Max Activating Token Index: 389

Text #14

Max Range: 1.4264. Min Range: -1.4264

Max Act: 0.5428. Min Act: -0.0000

Data Index: 251113 (C4 (Web Text))

Max Activating Token Index: 709

Text #15

Max Range: 1.4264. Min Range: -1.4264

Max Act: 0.5256. Min Act: -0.0000

Data Index: 1165277 (C4 (Web Text))

Max Activating Token Index: 672

Text #16

Max Range: 1.4264. Min Range: -1.4264

Max Act: 0.5115. Min Act: -0.0000

Data Index: 1210800 (C4 (Web Text))

Max Activating Token Index: 615

Text #17

Max Range: 1.4264. Min Range: -1.4264

Max Act: 0.5056. Min Act: -0.0000

Data Index: 614499 (C4 (Web Text))

Max Activating Token Index: 176

Text #18

Max Range: 1.4264. Min Range: -1.4264

Max Act: 0.5127. Min Act: -0.0000

Data Index: 77725 (C4 (Web Text))

Max Activating Token Index: 108

Text #19

Max Range: 1.4264. Min Range: -1.4264

Max Act: 0.4854. Min Act: -0.0000

Data Index: 673649 (C4 (Web Text))

Max Activating Token Index: 1016