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

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

Neuron 2676 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: 0.0302. Min Range: -0.0302

Max Act: 0.0302. Min Act: -0.0003

Data Index: 335709 (C4 (Web Text))

Max Activating Token Index: 244

Text #1

Max Range: 0.0302. Min Range: -0.0302

Max Act: 0.0241. Min Act: -0.0003

Data Index: 27517 (C4 (Web Text))

Max Activating Token Index: 3

Text #2

Max Range: 0.0302. Min Range: -0.0302

Max Act: 0.0236. Min Act: -0.0002

Data Index: 687888 (C4 (Web Text))

Max Activating Token Index: 15

Text #3

Max Range: 0.0302. Min Range: -0.0302

Max Act: 0.0234. Min Act: -0.0003

Data Index: 960261 (C4 (Web Text))

Max Activating Token Index: 21

Text #4

Max Range: 0.0302. Min Range: -0.0302

Max Act: 0.0217. Min Act: -0.0002

Data Index: 616042 (C4 (Web Text))

Max Activating Token Index: 3

Text #5

Max Range: 0.0302. Min Range: -0.0302

Max Act: 0.0222. Min Act: -0.0003

Data Index: 710471 (C4 (Web Text))

Max Activating Token Index: 731

Text #6

Max Range: 0.0302. Min Range: -0.0302

Max Act: 0.0215. Min Act: -0.0003

Data Index: 1107881 (C4 (Web Text))

Max Activating Token Index: 5

Text #7

Max Range: 0.0302. Min Range: -0.0302

Max Act: 0.0212. Min Act: -0.0003

Data Index: 1214139 (C4 (Web Text))

Max Activating Token Index: 7

Text #8

Max Range: 0.0302. Min Range: -0.0302

Max Act: 0.0216. Min Act: -0.0003

Data Index: 859336 (C4 (Web Text))

Max Activating Token Index: 715

Text #9

Max Range: 0.0302. Min Range: -0.0302

Max Act: 0.0207. Min Act: -0.0003

Data Index: 538073 (C4 (Web Text))

Max Activating Token Index: 195

Text #10

Max Range: 0.0302. Min Range: -0.0302

Max Act: 0.0206. Min Act: -0.0003

Data Index: 794133 (C4 (Web Text))

Max Activating Token Index: 680

Text #11

Max Range: 0.0302. Min Range: -0.0302

Max Act: 0.0203. Min Act: -0.0002

Data Index: 1083937 (C4 (Web Text))

Max Activating Token Index: 16

Text #12

Max Range: 0.0302. Min Range: -0.0302

Max Act: 0.0197. Min Act: -0.0002

Data Index: 823276 (C4 (Web Text))

Max Activating Token Index: 25

Text #13

Max Range: 0.0302. Min Range: -0.0302

Max Act: 0.0202. Min Act: -0.0003

Data Index: 660497 (C4 (Web Text))

Max Activating Token Index: 202

Text #14

Max Range: 0.0302. Min Range: -0.0302

Max Act: 0.0198. Min Act: -0.0002

Data Index: 556629 (C4 (Web Text))

Max Activating Token Index: 7

Text #15

Max Range: 0.0302. Min Range: -0.0302

Max Act: 0.0205. Min Act: -0.0003

Data Index: 1288668 (C4 (Web Text))

Max Activating Token Index: 133

Text #16

Max Range: 0.0302. Min Range: -0.0302

Max Act: 0.0199. Min Act: -0.0003

Data Index: 1086884 (C4 (Web Text))

Max Activating Token Index: 14

Text #17

Max Range: 0.0302. Min Range: -0.0302

Max Act: 0.0196. Min Act: -0.0003

Data Index: 726999 (C4 (Web Text))

Max Activating Token Index: 814

Text #18

Max Range: 0.0302. Min Range: -0.0302

Max Act: 0.0189. Min Act: -0.0003

Data Index: 1328196 (C4 (Web Text))

Max Activating Token Index: 1003

Text #19

Max Range: 0.0302. Min Range: -0.0302

Max Act: 0.0186. Min Act: -0.0003

Data Index: 166172 (C4 (Web Text))

Max Activating Token Index: 5