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

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

Neuron 4754 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0276. Min Range: -0.0276

Max Act: 0.0276. Min Act: -0.0002

Data Index: 726318 (C4 (Web Text))

Max Activating Token Index: 50

Text #1

Max Range: 0.0276. Min Range: -0.0276

Max Act: 0.0271. Min Act: -0.0002

Data Index: 182863 (C4 (Web Text))

Max Activating Token Index: 21

Text #2

Max Range: 0.0276. Min Range: -0.0276

Max Act: 0.0264. Min Act: -0.0002

Data Index: 939182 (C4 (Web Text))

Max Activating Token Index: 442

Text #3

Max Range: 0.0276. Min Range: -0.0276

Max Act: 0.0255. Min Act: -0.0002

Data Index: 894559 (C4 (Web Text))

Max Activating Token Index: 62

Text #4

Max Range: 0.0276. Min Range: -0.0276

Max Act: 0.0254. Min Act: -0.0002

Data Index: 113155 (C4 (Web Text))

Max Activating Token Index: 457

Text #5

Max Range: 0.0276. Min Range: -0.0276

Max Act: 0.0254. Min Act: -0.0002

Data Index: 399140 (C4 (Web Text))

Max Activating Token Index: 50

Text #6

Max Range: 0.0276. Min Range: -0.0276

Max Act: 0.0243. Min Act: -0.0002

Data Index: 852560 (C4 (Web Text))

Max Activating Token Index: 541

Text #7

Max Range: 0.0276. Min Range: -0.0276

Max Act: 0.0229. Min Act: -0.0002

Data Index: 954850 (C4 (Web Text))

Max Activating Token Index: 283

Text #8

Max Range: 0.0276. Min Range: -0.0276

Max Act: 0.0225. Min Act: -0.0002

Data Index: 714527 (C4 (Web Text))

Max Activating Token Index: 814

Text #9

Max Range: 0.0276. Min Range: -0.0276

Max Act: 0.0224. Min Act: -0.0002

Data Index: 268992 (C4 (Web Text))

Max Activating Token Index: 505

Text #10

Max Range: 0.0276. Min Range: -0.0276

Max Act: 0.0223. Min Act: -0.0002

Data Index: 939516 (C4 (Web Text))

Max Activating Token Index: 46

Text #11

Max Range: 0.0276. Min Range: -0.0276

Max Act: 0.0221. Min Act: -0.0002

Data Index: 568322 (C4 (Web Text))

Max Activating Token Index: 99

Text #12

Max Range: 0.0276. Min Range: -0.0276

Max Act: 0.0220. Min Act: -0.0002

Data Index: 1343716 (C4 (Web Text))

Max Activating Token Index: 12

Text #13

Max Range: 0.0276. Min Range: -0.0276

Max Act: 0.0211. Min Act: -0.0002

Data Index: 881372 (C4 (Web Text))

Max Activating Token Index: 299

Text #14

Max Range: 0.0276. Min Range: -0.0276

Max Act: 0.0212. Min Act: -0.0002

Data Index: 315774 (C4 (Web Text))

Max Activating Token Index: 175

Text #15

Max Range: 0.0276. Min Range: -0.0276

Max Act: 0.0209. Min Act: -0.0002

Data Index: 798343 (C4 (Web Text))

Max Activating Token Index: 484

Text #16

Max Range: 0.0276. Min Range: -0.0276

Max Act: 0.0206. Min Act: -0.0002

Data Index: 655210 (C4 (Web Text))

Max Activating Token Index: 354

Text #17

Max Range: 0.0276. Min Range: -0.0276

Max Act: 0.0208. Min Act: -0.0002

Data Index: 477372 (C4 (Web Text))

Max Activating Token Index: 779

Text #18

Max Range: 0.0276. Min Range: -0.0276

Max Act: 0.0207. Min Act: -0.0002

Data Index: 315514 (C4 (Web Text))

Max Activating Token Index: 671

Text #19

Max Range: 0.0276. Min Range: -0.0276

Max Act: 0.0210. Min Act: -0.0002

Data Index: 291262 (C4 (Web Text))

Max Activating Token Index: 513