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

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

Neuron 84 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0254. Min Range: -0.0254

Max Act: 0.0254. Min Act: -0.0002

Data Index: 782342 (C4 (Web Text))

Max Activating Token Index: 518

Text #1

Max Range: 0.0254. Min Range: -0.0254

Max Act: 0.0252. Min Act: -0.0003

Data Index: 330617 (C4 (Web Text))

Max Activating Token Index: 656

Text #2

Max Range: 0.0254. Min Range: -0.0254

Max Act: 0.0246. Min Act: -0.0002

Data Index: 943542 (C4 (Web Text))

Max Activating Token Index: 761

Text #3

Max Range: 0.0254. Min Range: -0.0254

Max Act: 0.0236. Min Act: -0.0003

Data Index: 601674 (C4 (Web Text))

Max Activating Token Index: 497

Text #4

Max Range: 0.0254. Min Range: -0.0254

Max Act: 0.0230. Min Act: -0.0003

Data Index: 846045 (C4 (Web Text))

Max Activating Token Index: 288

Text #5

Max Range: 0.0254. Min Range: -0.0254

Max Act: 0.0223. Min Act: -0.0002

Data Index: 86436 (C4 (Web Text))

Max Activating Token Index: 269

Text #6

Max Range: 0.0254. Min Range: -0.0254

Max Act: 0.0222. Min Act: -0.0003

Data Index: 437119 (C4 (Web Text))

Max Activating Token Index: 640

Text #7

Max Range: 0.0254. Min Range: -0.0254

Max Act: 0.0212. Min Act: -0.0002

Data Index: 1631080 (Python Code)

Max Activating Token Index: 574

Text #8

Max Range: 0.0254. Min Range: -0.0254

Max Act: 0.0207. Min Act: -0.0003

Data Index: 1022028 (C4 (Web Text))

Max Activating Token Index: 791

Text #9

Max Range: 0.0254. Min Range: -0.0254

Max Act: 0.0210. Min Act: -0.0002

Data Index: 1421277 (Python Code)

Max Activating Token Index: 941

Text #10

Max Range: 0.0254. Min Range: -0.0254

Max Act: 0.0208. Min Act: -0.0003

Data Index: 238657 (C4 (Web Text))

Max Activating Token Index: 938

Text #11

Max Range: 0.0254. Min Range: -0.0254

Max Act: 0.0208. Min Act: -0.0002

Data Index: 1407667 (Python Code)

Max Activating Token Index: 389

Text #12

Max Range: 0.0254. Min Range: -0.0254

Max Act: 0.0208. Min Act: -0.0002

Data Index: 1386640 (Python Code)

Max Activating Token Index: 317

Text #13

Max Range: 0.0254. Min Range: -0.0254

Max Act: 0.0206. Min Act: -0.0003

Data Index: 1147268 (C4 (Web Text))

Max Activating Token Index: 742

Text #14

Max Range: 0.0254. Min Range: -0.0254

Max Act: 0.0198. Min Act: -0.0003

Data Index: 839635 (C4 (Web Text))

Max Activating Token Index: 718

Text #15

Max Range: 0.0254. Min Range: -0.0254

Max Act: 0.0194. Min Act: -0.0002

Data Index: 1491631 (Python Code)

Max Activating Token Index: 524

Text #16

Max Range: 0.0254. Min Range: -0.0254

Max Act: 0.0195. Min Act: -0.0002

Data Index: 1429457 (Python Code)

Max Activating Token Index: 922

Text #17

Max Range: 0.0254. Min Range: -0.0254

Max Act: 0.0194. Min Act: -0.0002

Data Index: 1463606 (Python Code)

Max Activating Token Index: 425

Text #18

Max Range: 0.0254. Min Range: -0.0254

Max Act: 0.0194. Min Act: -0.0002

Data Index: 1583786 (Python Code)

Max Activating Token Index: 1001

Text #19

Max Range: 0.0254. Min Range: -0.0254

Max Act: 0.0192. Min Act: -0.0002

Data Index: 606998 (C4 (Web Text))

Max Activating Token Index: 988