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

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

Neuron 3410 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: 0.0275. Min Range: -0.0275

Max Act: 0.0275. Min Act: -0.0002

Data Index: 1056831 (C4 (Web Text))

Max Activating Token Index: 886

Text #1

Max Range: 0.0275. Min Range: -0.0275

Max Act: 0.0253. Min Act: -0.0002

Data Index: 211925 (C4 (Web Text))

Max Activating Token Index: 4

Text #2

Max Range: 0.0275. Min Range: -0.0275

Max Act: 0.0246. Min Act: -0.0002

Data Index: 925022 (C4 (Web Text))

Max Activating Token Index: 948

Text #3

Max Range: 0.0275. Min Range: -0.0275

Max Act: 0.0248. Min Act: -0.0002

Data Index: 1055400 (C4 (Web Text))

Max Activating Token Index: 201

Text #4

Max Range: 0.0275. Min Range: -0.0275

Max Act: 0.0238. Min Act: -0.0002

Data Index: 871459 (C4 (Web Text))

Max Activating Token Index: 336

Text #5

Max Range: 0.0275. Min Range: -0.0275

Max Act: 0.0228. Min Act: -0.0002

Data Index: 131803 (C4 (Web Text))

Max Activating Token Index: 11

Text #6

Max Range: 0.0275. Min Range: -0.0275

Max Act: 0.0215. Min Act: -0.0002

Data Index: 1072690 (C4 (Web Text))

Max Activating Token Index: 843

Text #7

Max Range: 0.0275. Min Range: -0.0275

Max Act: 0.0238. Min Act: -0.0002

Data Index: 195761 (C4 (Web Text))

Max Activating Token Index: 13

Text #8

Max Range: 0.0275. Min Range: -0.0275

Max Act: 0.0233. Min Act: -0.0002

Data Index: 19713 (C4 (Web Text))

Max Activating Token Index: 880

Text #9

Max Range: 0.0275. Min Range: -0.0275

Max Act: 0.0226. Min Act: -0.0002

Data Index: 788435 (C4 (Web Text))

Max Activating Token Index: 31

Text #10

Max Range: 0.0275. Min Range: -0.0275

Max Act: 0.0199. Min Act: -0.0002

Data Index: 761329 (C4 (Web Text))

Max Activating Token Index: 151

Text #11

Max Range: 0.0275. Min Range: -0.0275

Max Act: 0.0222. Min Act: -0.0002

Data Index: 500168 (C4 (Web Text))

Max Activating Token Index: 8

Text #12

Max Range: 0.0275. Min Range: -0.0275

Max Act: 0.0223. Min Act: -0.0002

Data Index: 198838 (C4 (Web Text))

Max Activating Token Index: 732

Text #13

Max Range: 0.0275. Min Range: -0.0275

Max Act: 0.0225. Min Act: -0.0002

Data Index: 540553 (C4 (Web Text))

Max Activating Token Index: 505

Text #14

Max Range: 0.0275. Min Range: -0.0275

Max Act: 0.0218. Min Act: -0.0002

Data Index: 13125 (C4 (Web Text))

Max Activating Token Index: 378

Text #15

Max Range: 0.0275. Min Range: -0.0275

Max Act: 0.0203. Min Act: -0.0002

Data Index: 1011905 (C4 (Web Text))

Max Activating Token Index: 8

Text #16

Max Range: 0.0275. Min Range: -0.0275

Max Act: 0.0193. Min Act: -0.0002

Data Index: 1127457 (C4 (Web Text))

Max Activating Token Index: 6

Text #17

Max Range: 0.0275. Min Range: -0.0275

Max Act: 0.0209. Min Act: -0.0002

Data Index: 974875 (C4 (Web Text))

Max Activating Token Index: 4

Text #18

Max Range: 0.0275. Min Range: -0.0275

Max Act: 0.0202. Min Act: -0.0002

Data Index: 623435 (C4 (Web Text))

Max Activating Token Index: 16

Text #19

Max Range: 0.0275. Min Range: -0.0275

Max Act: 0.0175. Min Act: -0.0002

Data Index: 1183007 (C4 (Web Text))

Max Activating Token Index: 282