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

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

Neuron 3918 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0395. Min Range: -0.0395

Max Act: 0.0395. Min Act: -0.0002

Data Index: 1341337 (C4 (Web Text))

Max Activating Token Index: 845

Text #1

Max Range: 0.0395. Min Range: -0.0395

Max Act: 0.0337. Min Act: -0.0002

Data Index: 110963 (C4 (Web Text))

Max Activating Token Index: 483

Text #2

Max Range: 0.0395. Min Range: -0.0395

Max Act: 0.0254. Min Act: -0.0002

Data Index: 78550 (C4 (Web Text))

Max Activating Token Index: 834

Text #3

Max Range: 0.0395. Min Range: -0.0395

Max Act: 0.0230. Min Act: -0.0002

Data Index: 1085900 (C4 (Web Text))

Max Activating Token Index: 288

Text #4

Max Range: 0.0395. Min Range: -0.0395

Max Act: 0.0228. Min Act: -0.0002

Data Index: 365599 (C4 (Web Text))

Max Activating Token Index: 229

Text #5

Max Range: 0.0395. Min Range: -0.0395

Max Act: 0.0221. Min Act: -0.0002

Data Index: 661871 (C4 (Web Text))

Max Activating Token Index: 707

Text #6

Max Range: 0.0395. Min Range: -0.0395

Max Act: 0.0234. Min Act: -0.0002

Data Index: 945357 (C4 (Web Text))

Max Activating Token Index: 389

Text #7

Max Range: 0.0395. Min Range: -0.0395

Max Act: 0.0248. Min Act: -0.0002

Data Index: 1028864 (C4 (Web Text))

Max Activating Token Index: 5

Text #8

Max Range: 0.0395. Min Range: -0.0395

Max Act: 0.0237. Min Act: -0.0002

Data Index: 1269962 (C4 (Web Text))

Max Activating Token Index: 342

Text #9

Max Range: 0.0395. Min Range: -0.0395

Max Act: 0.0253. Min Act: -0.0002

Data Index: 546177 (C4 (Web Text))

Max Activating Token Index: 434

Text #10

Max Range: 0.0395. Min Range: -0.0395

Max Act: 0.0243. Min Act: -0.0002

Data Index: 109349 (C4 (Web Text))

Max Activating Token Index: 252

Text #11

Max Range: 0.0395. Min Range: -0.0395

Max Act: 0.0202. Min Act: -0.0002

Data Index: 559136 (C4 (Web Text))

Max Activating Token Index: 753

Text #12

Max Range: 0.0395. Min Range: -0.0395

Max Act: 0.0198. Min Act: -0.0002

Data Index: 1055912 (C4 (Web Text))

Max Activating Token Index: 269

Text #13

Max Range: 0.0395. Min Range: -0.0395

Max Act: 0.0187. Min Act: -0.0002

Data Index: 1083990 (C4 (Web Text))

Max Activating Token Index: 304

Text #14

Max Range: 0.0395. Min Range: -0.0395

Max Act: 0.0228. Min Act: -0.0002

Data Index: 1004584 (C4 (Web Text))

Max Activating Token Index: 1010

Text #15

Max Range: 0.0395. Min Range: -0.0395

Max Act: 0.0192. Min Act: -0.0002

Data Index: 465835 (C4 (Web Text))

Max Activating Token Index: 755

Text #16

Max Range: 0.0395. Min Range: -0.0395

Max Act: 0.0222. Min Act: -0.0002

Data Index: 1310798 (C4 (Web Text))

Max Activating Token Index: 1004

Text #17

Max Range: 0.0395. Min Range: -0.0395

Max Act: 0.0213. Min Act: -0.0002

Data Index: 279761 (C4 (Web Text))

Max Activating Token Index: 397

Text #18

Max Range: 0.0395. Min Range: -0.0395

Max Act: 0.0226. Min Act: -0.0002

Data Index: 249500 (C4 (Web Text))

Max Activating Token Index: 906

Text #19

Max Range: 0.0395. Min Range: -0.0395

Max Act: 0.0205. Min Act: -0.0002

Data Index: 429883 (C4 (Web Text))

Max Activating Token Index: 346