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

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

Neuron 5312 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: 0.0907. Min Range: -0.0907

Max Act: 0.0907. Min Act: -0.0002

Data Index: 1199327 (C4 (Web Text))

Max Activating Token Index: 364

Text #1

Max Range: 0.0907. Min Range: -0.0907

Max Act: 0.0255. Min Act: -0.0002

Data Index: 204034 (C4 (Web Text))

Max Activating Token Index: 303

Text #2

Max Range: 0.0907. Min Range: -0.0907

Max Act: 0.0244. Min Act: -0.0002

Data Index: 1396346 (Python Code)

Max Activating Token Index: 318

Text #3

Max Range: 0.0907. Min Range: -0.0907

Max Act: 0.0253. Min Act: -0.0002

Data Index: 760427 (C4 (Web Text))

Max Activating Token Index: 929

Text #4

Max Range: 0.0907. Min Range: -0.0907

Max Act: 0.0242. Min Act: -0.0002

Data Index: 1510391 (Python Code)

Max Activating Token Index: 563

Text #5

Max Range: 0.0907. Min Range: -0.0907

Max Act: 0.0236. Min Act: -0.0002

Data Index: 1197379 (C4 (Web Text))

Max Activating Token Index: 143

Text #6

Max Range: 0.0907. Min Range: -0.0907

Max Act: 0.0223. Min Act: -0.0002

Data Index: 1530242 (Python Code)

Max Activating Token Index: 29

Text #7

Max Range: 0.0907. Min Range: -0.0907

Max Act: 0.0222. Min Act: -0.0002

Data Index: 1225867 (C4 (Web Text))

Max Activating Token Index: 371

Text #8

Max Range: 0.0907. Min Range: -0.0907

Max Act: 0.0213. Min Act: -0.0002

Data Index: 118511 (C4 (Web Text))

Max Activating Token Index: 713

Text #9

Max Range: 0.0907. Min Range: -0.0907

Max Act: 0.0209. Min Act: -0.0002

Data Index: 380976 (C4 (Web Text))

Max Activating Token Index: 437

Text #10

Max Range: 0.0907. Min Range: -0.0907

Max Act: 0.0208. Min Act: -0.0002

Data Index: 84688 (C4 (Web Text))

Max Activating Token Index: 455

Text #11

Max Range: 0.0907. Min Range: -0.0907

Max Act: 0.0206. Min Act: -0.0002

Data Index: 358068 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 0.0907. Min Range: -0.0907

Max Act: 0.0206. Min Act: -0.0002

Data Index: 335373 (C4 (Web Text))

Max Activating Token Index: 939

Text #13

Max Range: 0.0907. Min Range: -0.0907

Max Act: 0.0198. Min Act: -0.0002

Data Index: 46375 (C4 (Web Text))

Max Activating Token Index: 196

Text #14

Max Range: 0.0907. Min Range: -0.0907

Max Act: 0.0200. Min Act: -0.0002

Data Index: 184664 (C4 (Web Text))

Max Activating Token Index: 54

Text #15

Max Range: 0.0907. Min Range: -0.0907

Max Act: 0.0197. Min Act: -0.0002

Data Index: 247633 (C4 (Web Text))

Max Activating Token Index: 804

Text #16

Max Range: 0.0907. Min Range: -0.0907

Max Act: 0.0195. Min Act: -0.0002

Data Index: 959913 (C4 (Web Text))

Max Activating Token Index: 220

Text #17

Max Range: 0.0907. Min Range: -0.0907

Max Act: 0.0202. Min Act: -0.0002

Data Index: 1339452 (C4 (Web Text))

Max Activating Token Index: 175

Text #18

Max Range: 0.0907. Min Range: -0.0907

Max Act: 0.0195. Min Act: -0.0002

Data Index: 476133 (C4 (Web Text))

Max Activating Token Index: 530

Text #19

Max Range: 0.0907. Min Range: -0.0907

Max Act: 0.0188. Min Act: -0.0002

Data Index: 481520 (C4 (Web Text))

Max Activating Token Index: 661