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

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

Neuron 1063 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: 0.0268. Min Range: -0.0268

Max Act: 0.0268. Min Act: -0.0002

Data Index: 1155165 (C4 (Web Text))

Max Activating Token Index: 780

Text #1

Max Range: 0.0268. Min Range: -0.0268

Max Act: 0.0250. Min Act: -0.0002

Data Index: 30332 (C4 (Web Text))

Max Activating Token Index: 668

Text #2

Max Range: 0.0268. Min Range: -0.0268

Max Act: 0.0225. Min Act: -0.0002

Data Index: 333016 (C4 (Web Text))

Max Activating Token Index: 192

Text #3

Max Range: 0.0268. Min Range: -0.0268

Max Act: 0.0223. Min Act: -0.0002

Data Index: 486816 (C4 (Web Text))

Max Activating Token Index: 164

Text #4

Max Range: 0.0268. Min Range: -0.0268

Max Act: 0.0236. Min Act: -0.0002

Data Index: 1318543 (C4 (Web Text))

Max Activating Token Index: 441

Text #5

Max Range: 0.0268. Min Range: -0.0268

Max Act: 0.0234. Min Act: -0.0002

Data Index: 520413 (C4 (Web Text))

Max Activating Token Index: 563

Text #6

Max Range: 0.0268. Min Range: -0.0268

Max Act: 0.0197. Min Act: -0.0002

Data Index: 490459 (C4 (Web Text))

Max Activating Token Index: 225

Text #7

Max Range: 0.0268. Min Range: -0.0268

Max Act: 0.0191. Min Act: -0.0002

Data Index: 599904 (C4 (Web Text))

Max Activating Token Index: 130

Text #8

Max Range: 0.0268. Min Range: -0.0268

Max Act: 0.0204. Min Act: -0.0002

Data Index: 455270 (C4 (Web Text))

Max Activating Token Index: 226

Text #9

Max Range: 0.0268. Min Range: -0.0268

Max Act: 0.0186. Min Act: -0.0002

Data Index: 722274 (C4 (Web Text))

Max Activating Token Index: 527

Text #10

Max Range: 0.0268. Min Range: -0.0268

Max Act: 0.0186. Min Act: -0.0002

Data Index: 1336975 (C4 (Web Text))

Max Activating Token Index: 794

Text #11

Max Range: 0.0268. Min Range: -0.0268

Max Act: 0.0193. Min Act: -0.0002

Data Index: 296019 (C4 (Web Text))

Max Activating Token Index: 42

Text #12

Max Range: 0.0268. Min Range: -0.0268

Max Act: 0.0186. Min Act: -0.0002

Data Index: 1457826 (Python Code)

Max Activating Token Index: 924

Text #13

Max Range: 0.0268. Min Range: -0.0268

Max Act: 0.0183. Min Act: -0.0002

Data Index: 1417 (C4 (Web Text))

Max Activating Token Index: 358

Text #14

Max Range: 0.0268. Min Range: -0.0268

Max Act: 0.0191. Min Act: -0.0002

Data Index: 192013 (C4 (Web Text))

Max Activating Token Index: 773

Text #15

Max Range: 0.0268. Min Range: -0.0268

Max Act: 0.0181. Min Act: -0.0002

Data Index: 34199 (C4 (Web Text))

Max Activating Token Index: 154

Text #16

Max Range: 0.0268. Min Range: -0.0268

Max Act: 0.0187. Min Act: -0.0002

Data Index: 1351461 (C4 (Web Text))

Max Activating Token Index: 135

Text #17

Max Range: 0.0268. Min Range: -0.0268

Max Act: 0.0200. Min Act: -0.0002

Data Index: 1035812 (C4 (Web Text))

Max Activating Token Index: 791

Text #18

Max Range: 0.0268. Min Range: -0.0268

Max Act: 0.0198. Min Act: -0.0002

Data Index: 630478 (C4 (Web Text))

Max Activating Token Index: 717

Text #19

Max Range: 0.0268. Min Range: -0.0268

Max Act: 0.0183. Min Act: -0.0002

Data Index: 1245392 (C4 (Web Text))

Max Activating Token Index: 52