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

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

Neuron 2009 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: 0.0234. Min Range: -0.0234

Max Act: 0.0234. Min Act: -0.0006

Data Index: 78843 (C4 (Web Text))

Max Activating Token Index: 980

Text #1

Max Range: 0.0234. Min Range: -0.0234

Max Act: 0.0232. Min Act: -0.0006

Data Index: 726619 (C4 (Web Text))

Max Activating Token Index: 673

Text #2

Max Range: 0.0234. Min Range: -0.0234

Max Act: 0.0224. Min Act: -0.0006

Data Index: 639652 (C4 (Web Text))

Max Activating Token Index: 543

Text #3

Max Range: 0.0234. Min Range: -0.0234

Max Act: 0.0225. Min Act: -0.0006

Data Index: 277590 (C4 (Web Text))

Max Activating Token Index: 609

Text #4

Max Range: 0.0234. Min Range: -0.0234

Max Act: 0.0223. Min Act: -0.0006

Data Index: 135915 (C4 (Web Text))

Max Activating Token Index: 748

Text #5

Max Range: 0.0234. Min Range: -0.0234

Max Act: 0.0207. Min Act: -0.0006

Data Index: 976070 (C4 (Web Text))

Max Activating Token Index: 65

Text #6

Max Range: 0.0234. Min Range: -0.0234

Max Act: 0.0212. Min Act: -0.0006

Data Index: 474164 (C4 (Web Text))

Max Activating Token Index: 497

Text #7

Max Range: 0.0234. Min Range: -0.0234

Max Act: 0.0194. Min Act: -0.0006

Data Index: 1012833 (C4 (Web Text))

Max Activating Token Index: 268

Text #8

Max Range: 0.0234. Min Range: -0.0234

Max Act: 0.0192. Min Act: -0.0006

Data Index: 511475 (C4 (Web Text))

Max Activating Token Index: 302

Text #9

Max Range: 0.0234. Min Range: -0.0234

Max Act: 0.0188. Min Act: -0.0005

Data Index: 407901 (C4 (Web Text))

Max Activating Token Index: 879

Text #10

Max Range: 0.0234. Min Range: -0.0234

Max Act: 0.0196. Min Act: -0.0006

Data Index: 193669 (C4 (Web Text))

Max Activating Token Index: 82

Text #11

Max Range: 0.0234. Min Range: -0.0234

Max Act: 0.0191. Min Act: -0.0006

Data Index: 711212 (C4 (Web Text))

Max Activating Token Index: 370

Text #12

Max Range: 0.0234. Min Range: -0.0234

Max Act: 0.0192. Min Act: -0.0006

Data Index: 1321467 (C4 (Web Text))

Max Activating Token Index: 931

Text #13

Max Range: 0.0234. Min Range: -0.0234

Max Act: 0.0189. Min Act: -0.0006

Data Index: 771509 (C4 (Web Text))

Max Activating Token Index: 4

Text #14

Max Range: 0.0234. Min Range: -0.0234

Max Act: 0.0187. Min Act: -0.0006

Data Index: 1239277 (C4 (Web Text))

Max Activating Token Index: 724

Text #15

Max Range: 0.0234. Min Range: -0.0234

Max Act: 0.0184. Min Act: -0.0006

Data Index: 489132 (C4 (Web Text))

Max Activating Token Index: 800

Text #16

Max Range: 0.0234. Min Range: -0.0234

Max Act: 0.0177. Min Act: -0.0006

Data Index: 1323107 (C4 (Web Text))

Max Activating Token Index: 834

Text #17

Max Range: 0.0234. Min Range: -0.0234

Max Act: 0.0187. Min Act: -0.0006

Data Index: 242282 (C4 (Web Text))

Max Activating Token Index: 139

Text #18

Max Range: 0.0234. Min Range: -0.0234

Max Act: 0.0183. Min Act: -0.0006

Data Index: 447769 (C4 (Web Text))

Max Activating Token Index: 33

Text #19

Max Range: 0.0234. Min Range: -0.0234

Max Act: 0.0179. Min Act: -0.0006

Data Index: 1160563 (C4 (Web Text))

Max Activating Token Index: 86