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

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

Neuron 481 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: 0.0333. Min Range: -0.0333

Max Act: 0.0333. Min Act: -0.0003

Data Index: 397203 (C4 (Web Text))

Max Activating Token Index: 222

Text #1

Max Range: 0.0333. Min Range: -0.0333

Max Act: 0.0293. Min Act: -0.0003

Data Index: 1306808 (C4 (Web Text))

Max Activating Token Index: 307

Text #2

Max Range: 0.0333. Min Range: -0.0333

Max Act: 0.0282. Min Act: -0.0003

Data Index: 466277 (C4 (Web Text))

Max Activating Token Index: 52

Text #3

Max Range: 0.0333. Min Range: -0.0333

Max Act: 0.0275. Min Act: -0.0003

Data Index: 609404 (C4 (Web Text))

Max Activating Token Index: 213

Text #4

Max Range: 0.0333. Min Range: -0.0333

Max Act: 0.0276. Min Act: -0.0002

Data Index: 860250 (C4 (Web Text))

Max Activating Token Index: 431

Text #5

Max Range: 0.0333. Min Range: -0.0333

Max Act: 0.0286. Min Act: -0.0002

Data Index: 909811 (C4 (Web Text))

Max Activating Token Index: 899

Text #6

Max Range: 0.0333. Min Range: -0.0333

Max Act: 0.0245. Min Act: -0.0002

Data Index: 728099 (C4 (Web Text))

Max Activating Token Index: 44

Text #7

Max Range: 0.0333. Min Range: -0.0333

Max Act: 0.0214. Min Act: -0.0002

Data Index: 204850 (C4 (Web Text))

Max Activating Token Index: 667

Text #8

Max Range: 0.0333. Min Range: -0.0333

Max Act: 0.0211. Min Act: -0.0002

Data Index: 1030595 (C4 (Web Text))

Max Activating Token Index: 112

Text #9

Max Range: 0.0333. Min Range: -0.0333

Max Act: 0.0209. Min Act: -0.0003

Data Index: 858073 (C4 (Web Text))

Max Activating Token Index: 320

Text #10

Max Range: 0.0333. Min Range: -0.0333

Max Act: 0.0198. Min Act: -0.0002

Data Index: 510429 (C4 (Web Text))

Max Activating Token Index: 6

Text #11

Max Range: 0.0333. Min Range: -0.0333

Max Act: 0.0190. Min Act: -0.0002

Data Index: 725099 (C4 (Web Text))

Max Activating Token Index: 438

Text #12

Max Range: 0.0333. Min Range: -0.0333

Max Act: 0.0189. Min Act: -0.0002

Data Index: 989865 (C4 (Web Text))

Max Activating Token Index: 23

Text #13

Max Range: 0.0333. Min Range: -0.0333

Max Act: 0.0178. Min Act: -0.0003

Data Index: 1202937 (C4 (Web Text))

Max Activating Token Index: 102

Text #14

Max Range: 0.0333. Min Range: -0.0333

Max Act: 0.0186. Min Act: -0.0003

Data Index: 1158302 (C4 (Web Text))

Max Activating Token Index: 717

Text #15

Max Range: 0.0333. Min Range: -0.0333

Max Act: 0.0187. Min Act: -0.0002

Data Index: 1261825 (C4 (Web Text))

Max Activating Token Index: 464

Text #16

Max Range: 0.0333. Min Range: -0.0333

Max Act: 0.0189. Min Act: -0.0002

Data Index: 83606 (C4 (Web Text))

Max Activating Token Index: 513

Text #17

Max Range: 0.0333. Min Range: -0.0333

Max Act: 0.0173. Min Act: -0.0003

Data Index: 13992 (C4 (Web Text))

Max Activating Token Index: 641

Text #18

Max Range: 0.0333. Min Range: -0.0333

Max Act: 0.0177. Min Act: -0.0003

Data Index: 1131840 (C4 (Web Text))

Max Activating Token Index: 136

Text #19

Max Range: 0.0333. Min Range: -0.0333

Max Act: 0.0174. Min Act: -0.0002

Data Index: 1101978 (C4 (Web Text))

Max Activating Token Index: 126