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

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

Neuron 2018 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0265. Min Range: -0.0265

Max Act: 0.0265. Min Act: -0.0004

Data Index: 1302494 (C4 (Web Text))

Max Activating Token Index: 8

Text #1

Max Range: 0.0265. Min Range: -0.0265

Max Act: 0.0261. Min Act: -0.0003

Data Index: 230784 (C4 (Web Text))

Max Activating Token Index: 942

Text #2

Max Range: 0.0265. Min Range: -0.0265

Max Act: 0.0236. Min Act: -0.0003

Data Index: 1440332 (Python Code)

Max Activating Token Index: 500

Text #3

Max Range: 0.0265. Min Range: -0.0265

Max Act: 0.0234. Min Act: -0.0003

Data Index: 1235325 (C4 (Web Text))

Max Activating Token Index: 189

Text #4

Max Range: 0.0265. Min Range: -0.0265

Max Act: 0.0236. Min Act: -0.0003

Data Index: 59635 (C4 (Web Text))

Max Activating Token Index: 7

Text #5

Max Range: 0.0265. Min Range: -0.0265

Max Act: 0.0229. Min Act: -0.0003

Data Index: 437318 (C4 (Web Text))

Max Activating Token Index: 898

Text #6

Max Range: 0.0265. Min Range: -0.0265

Max Act: 0.0218. Min Act: -0.0003

Data Index: 1152780 (C4 (Web Text))

Max Activating Token Index: 1020

Text #7

Max Range: 0.0265. Min Range: -0.0265

Max Act: 0.0231. Min Act: -0.0003

Data Index: 1447284 (Python Code)

Max Activating Token Index: 6

Text #8

Max Range: 0.0265. Min Range: -0.0265

Max Act: 0.0226. Min Act: -0.0003

Data Index: 942160 (C4 (Web Text))

Max Activating Token Index: 992

Text #9

Max Range: 0.0265. Min Range: -0.0265

Max Act: 0.0220. Min Act: -0.0003

Data Index: 257179 (C4 (Web Text))

Max Activating Token Index: 924

Text #10

Max Range: 0.0265. Min Range: -0.0265

Max Act: 0.0230. Min Act: -0.0003

Data Index: 1258471 (C4 (Web Text))

Max Activating Token Index: 41

Text #11

Max Range: 0.0265. Min Range: -0.0265

Max Act: 0.0206. Min Act: -0.0003

Data Index: 1130497 (C4 (Web Text))

Max Activating Token Index: 375

Text #12

Max Range: 0.0265. Min Range: -0.0265

Max Act: 0.0218. Min Act: -0.0003

Data Index: 1521181 (Python Code)

Max Activating Token Index: 656

Text #13

Max Range: 0.0265. Min Range: -0.0265

Max Act: 0.0212. Min Act: -0.0003

Data Index: 1588626 (Python Code)

Max Activating Token Index: 789

Text #14

Max Range: 0.0265. Min Range: -0.0265

Max Act: 0.0220. Min Act: -0.0003

Data Index: 1337830 (C4 (Web Text))

Max Activating Token Index: 440

Text #15

Max Range: 0.0265. Min Range: -0.0265

Max Act: 0.0229. Min Act: -0.0003

Data Index: 381793 (C4 (Web Text))

Max Activating Token Index: 57

Text #16

Max Range: 0.0265. Min Range: -0.0265

Max Act: 0.0229. Min Act: -0.0003

Data Index: 154600 (C4 (Web Text))

Max Activating Token Index: 584

Text #17

Max Range: 0.0265. Min Range: -0.0265

Max Act: 0.0213. Min Act: -0.0003

Data Index: 174855 (C4 (Web Text))

Max Activating Token Index: 122

Text #18

Max Range: 0.0265. Min Range: -0.0265

Max Act: 0.0230. Min Act: -0.0003

Data Index: 1635041 (Python Code)

Max Activating Token Index: 663

Text #19

Max Range: 0.0265. Min Range: -0.0265

Max Act: 0.0224. Min Act: -0.0003

Data Index: 1340504 (C4 (Web Text))

Max Activating Token Index: 7