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

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

Neuron 559 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0248. Min Range: -0.0248

Max Act: 0.0248. Min Act: -0.0002

Data Index: 227335 (C4 (Web Text))

Max Activating Token Index: 774

Text #1

Max Range: 0.0248. Min Range: -0.0248

Max Act: 0.0230. Min Act: -0.0002

Data Index: 623054 (C4 (Web Text))

Max Activating Token Index: 32

Text #2

Max Range: 0.0248. Min Range: -0.0248

Max Act: 0.0234. Min Act: -0.0002

Data Index: 969943 (C4 (Web Text))

Max Activating Token Index: 3

Text #3

Max Range: 0.0248. Min Range: -0.0248

Max Act: 0.0234. Min Act: -0.0002

Data Index: 731460 (C4 (Web Text))

Max Activating Token Index: 1002

Text #4

Max Range: 0.0248. Min Range: -0.0248

Max Act: 0.0233. Min Act: -0.0002

Data Index: 309110 (C4 (Web Text))

Max Activating Token Index: 748

Text #5

Max Range: 0.0248. Min Range: -0.0248

Max Act: 0.0232. Min Act: -0.0002

Data Index: 319139 (C4 (Web Text))

Max Activating Token Index: 209

Text #6

Max Range: 0.0248. Min Range: -0.0248

Max Act: 0.0231. Min Act: -0.0002

Data Index: 1496455 (Python Code)

Max Activating Token Index: 6

Text #7

Max Range: 0.0248. Min Range: -0.0248

Max Act: 0.0230. Min Act: -0.0002

Data Index: 192835 (C4 (Web Text))

Max Activating Token Index: 651

Text #8

Max Range: 0.0248. Min Range: -0.0248

Max Act: 0.0229. Min Act: -0.0002

Data Index: 1038745 (C4 (Web Text))

Max Activating Token Index: 816

Text #9

Max Range: 0.0248. Min Range: -0.0248

Max Act: 0.0228. Min Act: -0.0002

Data Index: 1320822 (C4 (Web Text))

Max Activating Token Index: 698

Text #10

Max Range: 0.0248. Min Range: -0.0248

Max Act: 0.0228. Min Act: -0.0002

Data Index: 1058808 (C4 (Web Text))

Max Activating Token Index: 905

Text #11

Max Range: 0.0248. Min Range: -0.0248

Max Act: 0.0227. Min Act: -0.0002

Data Index: 128592 (C4 (Web Text))

Max Activating Token Index: 842

Text #12

Max Range: 0.0248. Min Range: -0.0248

Max Act: 0.0226. Min Act: -0.0002

Data Index: 685453 (C4 (Web Text))

Max Activating Token Index: 773

Text #13

Max Range: 0.0248. Min Range: -0.0248

Max Act: 0.0226. Min Act: -0.0002

Data Index: 550486 (C4 (Web Text))

Max Activating Token Index: 140

Text #14

Max Range: 0.0248. Min Range: -0.0248

Max Act: 0.0226. Min Act: -0.0002

Data Index: 1147731 (C4 (Web Text))

Max Activating Token Index: 863

Text #15

Max Range: 0.0248. Min Range: -0.0248

Max Act: 0.0224. Min Act: -0.0002

Data Index: 169894 (C4 (Web Text))

Max Activating Token Index: 996

Text #16

Max Range: 0.0248. Min Range: -0.0248

Max Act: 0.0224. Min Act: -0.0002

Data Index: 141861 (C4 (Web Text))

Max Activating Token Index: 8

Text #17

Max Range: 0.0248. Min Range: -0.0248

Max Act: 0.0228. Min Act: -0.0002

Data Index: 1034006 (C4 (Web Text))

Max Activating Token Index: 803

Text #18

Max Range: 0.0248. Min Range: -0.0248

Max Act: 0.0224. Min Act: -0.0002

Data Index: 718427 (C4 (Web Text))

Max Activating Token Index: 1022

Text #19

Max Range: 0.0248. Min Range: -0.0248

Max Act: 0.0218. Min Act: -0.0002

Data Index: 1045578 (C4 (Web Text))

Max Activating Token Index: 625