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

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

Neuron 488 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0338. Min Range: -0.0338

Max Act: 0.0338. Min Act: -0.0003

Data Index: 1280432 (C4 (Web Text))

Max Activating Token Index: 779

Text #1

Max Range: 0.0338. Min Range: -0.0338

Max Act: 0.0248. Min Act: -0.0002

Data Index: 531554 (C4 (Web Text))

Max Activating Token Index: 132

Text #2

Max Range: 0.0338. Min Range: -0.0338

Max Act: 0.0224. Min Act: -0.0003

Data Index: 449687 (C4 (Web Text))

Max Activating Token Index: 812

Text #3

Max Range: 0.0338. Min Range: -0.0338

Max Act: 0.0240. Min Act: -0.0003

Data Index: 166062 (C4 (Web Text))

Max Activating Token Index: 153

Text #4

Max Range: 0.0338. Min Range: -0.0338

Max Act: 0.0218. Min Act: -0.0003

Data Index: 620865 (C4 (Web Text))

Max Activating Token Index: 193

Text #5

Max Range: 0.0338. Min Range: -0.0338

Max Act: 0.0225. Min Act: -0.0003

Data Index: 73050 (C4 (Web Text))

Max Activating Token Index: 710

Text #6

Max Range: 0.0338. Min Range: -0.0338

Max Act: 0.0195. Min Act: -0.0003

Data Index: 579873 (C4 (Web Text))

Max Activating Token Index: 278

Text #7

Max Range: 0.0338. Min Range: -0.0338

Max Act: 0.0210. Min Act: -0.0003

Data Index: 49763 (C4 (Web Text))

Max Activating Token Index: 195

Text #8

Max Range: 0.0338. Min Range: -0.0338

Max Act: 0.0201. Min Act: -0.0003

Data Index: 828020 (C4 (Web Text))

Max Activating Token Index: 222

Text #9

Max Range: 0.0338. Min Range: -0.0338

Max Act: 0.0210. Min Act: -0.0003

Data Index: 1191247 (C4 (Web Text))

Max Activating Token Index: 735

Text #10

Max Range: 0.0338. Min Range: -0.0338

Max Act: 0.0208. Min Act: -0.0002

Data Index: 715081 (C4 (Web Text))

Max Activating Token Index: 138

Text #11

Max Range: 0.0338. Min Range: -0.0338

Max Act: 0.0204. Min Act: -0.0003

Data Index: 1035579 (C4 (Web Text))

Max Activating Token Index: 440

Text #12

Max Range: 0.0338. Min Range: -0.0338

Max Act: 0.0203. Min Act: -0.0003

Data Index: 203973 (C4 (Web Text))

Max Activating Token Index: 534

Text #13

Max Range: 0.0338. Min Range: -0.0338

Max Act: 0.0183. Min Act: -0.0003

Data Index: 1166866 (C4 (Web Text))

Max Activating Token Index: 266

Text #14

Max Range: 0.0338. Min Range: -0.0338

Max Act: 0.0214. Min Act: -0.0003

Data Index: 264958 (C4 (Web Text))

Max Activating Token Index: 65

Text #15

Max Range: 0.0338. Min Range: -0.0338

Max Act: 0.0198. Min Act: -0.0003

Data Index: 641950 (C4 (Web Text))

Max Activating Token Index: 55

Text #16

Max Range: 0.0338. Min Range: -0.0338

Max Act: 0.0194. Min Act: -0.0003

Data Index: 578848 (C4 (Web Text))

Max Activating Token Index: 324

Text #17

Max Range: 0.0338. Min Range: -0.0338

Max Act: 0.0183. Min Act: -0.0003

Data Index: 1249854 (C4 (Web Text))

Max Activating Token Index: 122

Text #18

Max Range: 0.0338. Min Range: -0.0338

Max Act: 0.0200. Min Act: -0.0003

Data Index: 234943 (C4 (Web Text))

Max Activating Token Index: 586

Text #19

Max Range: 0.0338. Min Range: -0.0338

Max Act: 0.0208. Min Act: -0.0003

Data Index: 831383 (C4 (Web Text))

Max Activating Token Index: 720