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

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

Neuron 4189 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: 0.0383. Min Range: -0.0383

Max Act: 0.0383. Min Act: -0.0003

Data Index: 656239 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.0383. Min Range: -0.0383

Max Act: 0.0367. Min Act: -0.0002

Data Index: 914615 (C4 (Web Text))

Max Activating Token Index: 796

Text #2

Max Range: 0.0383. Min Range: -0.0383

Max Act: 0.0300. Min Act: -0.0003

Data Index: 1174839 (C4 (Web Text))

Max Activating Token Index: 357

Text #3

Max Range: 0.0383. Min Range: -0.0383

Max Act: 0.0286. Min Act: -0.0003

Data Index: 722589 (C4 (Web Text))

Max Activating Token Index: 453

Text #4

Max Range: 0.0383. Min Range: -0.0383

Max Act: 0.0283. Min Act: -0.0003

Data Index: 1090229 (C4 (Web Text))

Max Activating Token Index: 593

Text #5

Max Range: 0.0383. Min Range: -0.0383

Max Act: 0.0253. Min Act: -0.0003

Data Index: 1006768 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 0.0383. Min Range: -0.0383

Max Act: 0.0257. Min Act: -0.0003

Data Index: 250558 (C4 (Web Text))

Max Activating Token Index: 112

Text #7

Max Range: 0.0383. Min Range: -0.0383

Max Act: 0.0250. Min Act: -0.0003

Data Index: 675844 (C4 (Web Text))

Max Activating Token Index: 217

Text #8

Max Range: 0.0383. Min Range: -0.0383

Max Act: 0.0270. Min Act: -0.0003

Data Index: 329891 (C4 (Web Text))

Max Activating Token Index: 308

Text #9

Max Range: 0.0383. Min Range: -0.0383

Max Act: 0.0211. Min Act: -0.0003

Data Index: 1263573 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 0.0383. Min Range: -0.0383

Max Act: 0.0263. Min Act: -0.0002

Data Index: 600230 (C4 (Web Text))

Max Activating Token Index: 86

Text #11

Max Range: 0.0383. Min Range: -0.0383

Max Act: 0.0224. Min Act: -0.0003

Data Index: 93505 (C4 (Web Text))

Max Activating Token Index: 274

Text #12

Max Range: 0.0383. Min Range: -0.0383

Max Act: 0.0268. Min Act: -0.0003

Data Index: 368968 (C4 (Web Text))

Max Activating Token Index: 6

Text #13

Max Range: 0.0383. Min Range: -0.0383

Max Act: 0.0281. Min Act: -0.0002

Data Index: 505153 (C4 (Web Text))

Max Activating Token Index: 787

Text #14

Max Range: 0.0383. Min Range: -0.0383

Max Act: 0.0244. Min Act: -0.0003

Data Index: 951743 (C4 (Web Text))

Max Activating Token Index: 850

Text #15

Max Range: 0.0383. Min Range: -0.0383

Max Act: 0.0233. Min Act: -0.0003

Data Index: 854917 (C4 (Web Text))

Max Activating Token Index: 713

Text #16

Max Range: 0.0383. Min Range: -0.0383

Max Act: 0.0205. Min Act: -0.0003

Data Index: 1302763 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 0.0383. Min Range: -0.0383

Max Act: 0.0240. Min Act: -0.0003

Data Index: 1206189 (C4 (Web Text))

Max Activating Token Index: 227

Text #18

Max Range: 0.0383. Min Range: -0.0383

Max Act: 0.0267. Min Act: -0.0003

Data Index: 8235 (C4 (Web Text))

Max Activating Token Index: 699

Text #19

Max Range: 0.0383. Min Range: -0.0383

Max Act: 0.0181. Min Act: -0.0003

Data Index: 169334 (C4 (Web Text))

Max Activating Token Index: 235