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

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

Neuron 2997 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0288. Min Range: -0.0288

Max Act: 0.0288. Min Act: -0.0001

Data Index: 400340 (C4 (Web Text))

Max Activating Token Index: 495

Text #1

Max Range: 0.0288. Min Range: -0.0288

Max Act: 0.0255. Min Act: -0.0001

Data Index: 1130768 (C4 (Web Text))

Max Activating Token Index: 280

Text #2

Max Range: 0.0288. Min Range: -0.0288

Max Act: 0.0220. Min Act: -0.0001

Data Index: 950595 (C4 (Web Text))

Max Activating Token Index: 357

Text #3

Max Range: 0.0288. Min Range: -0.0288

Max Act: 0.0229. Min Act: -0.0001

Data Index: 23382 (C4 (Web Text))

Max Activating Token Index: 595

Text #4

Max Range: 0.0288. Min Range: -0.0288

Max Act: 0.0226. Min Act: -0.0001

Data Index: 859913 (C4 (Web Text))

Max Activating Token Index: 31

Text #5

Max Range: 0.0288. Min Range: -0.0288

Max Act: 0.0226. Min Act: -0.0001

Data Index: 239941 (C4 (Web Text))

Max Activating Token Index: 119

Text #6

Max Range: 0.0288. Min Range: -0.0288

Max Act: 0.0231. Min Act: -0.0001

Data Index: 948669 (C4 (Web Text))

Max Activating Token Index: 126

Text #7

Max Range: 0.0288. Min Range: -0.0288

Max Act: 0.0234. Min Act: -0.0001

Data Index: 1109208 (C4 (Web Text))

Max Activating Token Index: 703

Text #8

Max Range: 0.0288. Min Range: -0.0288

Max Act: 0.0224. Min Act: -0.0001

Data Index: 718825 (C4 (Web Text))

Max Activating Token Index: 340

Text #9

Max Range: 0.0288. Min Range: -0.0288

Max Act: 0.0222. Min Act: -0.0001

Data Index: 534674 (C4 (Web Text))

Max Activating Token Index: 578

Text #10

Max Range: 0.0288. Min Range: -0.0288

Max Act: 0.0215. Min Act: -0.0001

Data Index: 1148571 (C4 (Web Text))

Max Activating Token Index: 136

Text #11

Max Range: 0.0288. Min Range: -0.0288

Max Act: 0.0216. Min Act: -0.0001

Data Index: 4279 (C4 (Web Text))

Max Activating Token Index: 64

Text #12

Max Range: 0.0288. Min Range: -0.0288

Max Act: 0.0216. Min Act: -0.0001

Data Index: 341849 (C4 (Web Text))

Max Activating Token Index: 491

Text #13

Max Range: 0.0288. Min Range: -0.0288

Max Act: 0.0217. Min Act: -0.0001

Data Index: 788158 (C4 (Web Text))

Max Activating Token Index: 259

Text #14

Max Range: 0.0288. Min Range: -0.0288

Max Act: 0.0206. Min Act: -0.0001

Data Index: 1482855 (Python Code)

Max Activating Token Index: 835

Text #15

Max Range: 0.0288. Min Range: -0.0288

Max Act: 0.0191. Min Act: -0.0001

Data Index: 886241 (C4 (Web Text))

Max Activating Token Index: 697

Text #16

Max Range: 0.0288. Min Range: -0.0288

Max Act: 0.0208. Min Act: -0.0001

Data Index: 586942 (C4 (Web Text))

Max Activating Token Index: 321

Text #17

Max Range: 0.0288. Min Range: -0.0288

Max Act: 0.0205. Min Act: -0.0001

Data Index: 1642365 (Python Code)

Max Activating Token Index: 609

Text #18

Max Range: 0.0288. Min Range: -0.0288

Max Act: 0.0203. Min Act: -0.0001

Data Index: 946039 (C4 (Web Text))

Max Activating Token Index: 783

Text #19

Max Range: 0.0288. Min Range: -0.0288

Max Act: 0.0189. Min Act: -0.0001

Data Index: 388 (C4 (Web Text))

Max Activating Token Index: 68