Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 2012 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0274. Min Range: -0.0274

Max Act: 0.0274. Min Act: -0.0006

Data Index: 20454 (C4 (Web Text))

Max Activating Token Index: 334

Text #1

Max Range: 0.0274. Min Range: -0.0274

Max Act: 0.0242. Min Act: -0.0006

Data Index: 301316 (C4 (Web Text))

Max Activating Token Index: 494

Text #2

Max Range: 0.0274. Min Range: -0.0274

Max Act: 0.0241. Min Act: -0.0006

Data Index: 808258 (C4 (Web Text))

Max Activating Token Index: 983

Text #3

Max Range: 0.0274. Min Range: -0.0274

Max Act: 0.0243. Min Act: -0.0006

Data Index: 451977 (C4 (Web Text))

Max Activating Token Index: 889

Text #4

Max Range: 0.0274. Min Range: -0.0274

Max Act: 0.0229. Min Act: -0.0006

Data Index: 78909 (C4 (Web Text))

Max Activating Token Index: 626

Text #5

Max Range: 0.0274. Min Range: -0.0274

Max Act: 0.0229. Min Act: -0.0006

Data Index: 753081 (C4 (Web Text))

Max Activating Token Index: 354

Text #6

Max Range: 0.0274. Min Range: -0.0274

Max Act: 0.0234. Min Act: -0.0006

Data Index: 570517 (C4 (Web Text))

Max Activating Token Index: 386

Text #7

Max Range: 0.0274. Min Range: -0.0274

Max Act: 0.0234. Min Act: -0.0006

Data Index: 1278340 (C4 (Web Text))

Max Activating Token Index: 16

Text #8

Max Range: 0.0274. Min Range: -0.0274

Max Act: 0.0222. Min Act: -0.0006

Data Index: 1089817 (C4 (Web Text))

Max Activating Token Index: 921

Text #9

Max Range: 0.0274. Min Range: -0.0274

Max Act: 0.0229. Min Act: -0.0006

Data Index: 858285 (C4 (Web Text))

Max Activating Token Index: 890

Text #10

Max Range: 0.0274. Min Range: -0.0274

Max Act: 0.0229. Min Act: -0.0006

Data Index: 660867 (C4 (Web Text))

Max Activating Token Index: 689

Text #11

Max Range: 0.0274. Min Range: -0.0274

Max Act: 0.0228. Min Act: -0.0006

Data Index: 705237 (C4 (Web Text))

Max Activating Token Index: 265

Text #12

Max Range: 0.0274. Min Range: -0.0274

Max Act: 0.0232. Min Act: -0.0006

Data Index: 1169343 (C4 (Web Text))

Max Activating Token Index: 911

Text #13

Max Range: 0.0274. Min Range: -0.0274

Max Act: 0.0219. Min Act: -0.0006

Data Index: 647705 (C4 (Web Text))

Max Activating Token Index: 34

Text #14

Max Range: 0.0274. Min Range: -0.0274

Max Act: 0.0224. Min Act: -0.0006

Data Index: 1334856 (C4 (Web Text))

Max Activating Token Index: 546

Text #15

Max Range: 0.0274. Min Range: -0.0274

Max Act: 0.0214. Min Act: -0.0006

Data Index: 1253662 (C4 (Web Text))

Max Activating Token Index: 910

Text #16

Max Range: 0.0274. Min Range: -0.0274

Max Act: 0.0222. Min Act: -0.0006

Data Index: 3788 (C4 (Web Text))

Max Activating Token Index: 136

Text #17

Max Range: 0.0274. Min Range: -0.0274

Max Act: 0.0207. Min Act: -0.0006

Data Index: 1304842 (C4 (Web Text))

Max Activating Token Index: 761

Text #18

Max Range: 0.0274. Min Range: -0.0274

Max Act: 0.0212. Min Act: -0.0006

Data Index: 629012 (C4 (Web Text))

Max Activating Token Index: 202

Text #19

Max Range: 0.0274. Min Range: -0.0274

Max Act: 0.0216. Min Act: -0.0006

Data Index: 619468 (C4 (Web Text))

Max Activating Token Index: 495