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

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

Neuron 4137 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: 0.0328. Min Range: -0.0328

Max Act: 0.0328. Min Act: -0.0003

Data Index: 184877 (C4 (Web Text))

Max Activating Token Index: 104

Text #1

Max Range: 0.0328. Min Range: -0.0328

Max Act: 0.0265. Min Act: -0.0003

Data Index: 998175 (C4 (Web Text))

Max Activating Token Index: 626

Text #2

Max Range: 0.0328. Min Range: -0.0328

Max Act: 0.0253. Min Act: -0.0003

Data Index: 709530 (C4 (Web Text))

Max Activating Token Index: 861

Text #3

Max Range: 0.0328. Min Range: -0.0328

Max Act: 0.0229. Min Act: -0.0003

Data Index: 1043834 (C4 (Web Text))

Max Activating Token Index: 574

Text #4

Max Range: 0.0328. Min Range: -0.0328

Max Act: 0.0229. Min Act: -0.0002

Data Index: 64937 (C4 (Web Text))

Max Activating Token Index: 239

Text #5

Max Range: 0.0328. Min Range: -0.0328

Max Act: 0.0210. Min Act: -0.0003

Data Index: 487602 (C4 (Web Text))

Max Activating Token Index: 527

Text #6

Max Range: 0.0328. Min Range: -0.0328

Max Act: 0.0206. Min Act: -0.0003

Data Index: 304038 (C4 (Web Text))

Max Activating Token Index: 847

Text #7

Max Range: 0.0328. Min Range: -0.0328

Max Act: 0.0202. Min Act: -0.0002

Data Index: 457329 (C4 (Web Text))

Max Activating Token Index: 272

Text #8

Max Range: 0.0328. Min Range: -0.0328

Max Act: 0.0200. Min Act: -0.0003

Data Index: 619791 (C4 (Web Text))

Max Activating Token Index: 87

Text #9

Max Range: 0.0328. Min Range: -0.0328

Max Act: 0.0199. Min Act: -0.0002

Data Index: 330001 (C4 (Web Text))

Max Activating Token Index: 1016

Text #10

Max Range: 0.0328. Min Range: -0.0328

Max Act: 0.0197. Min Act: -0.0003

Data Index: 1331912 (C4 (Web Text))

Max Activating Token Index: 700

Text #11

Max Range: 0.0328. Min Range: -0.0328

Max Act: 0.0183. Min Act: -0.0003

Data Index: 13360 (C4 (Web Text))

Max Activating Token Index: 576

Text #12

Max Range: 0.0328. Min Range: -0.0328

Max Act: 0.0191. Min Act: -0.0003

Data Index: 884762 (C4 (Web Text))

Max Activating Token Index: 207

Text #13

Max Range: 0.0328. Min Range: -0.0328

Max Act: 0.0185. Min Act: -0.0003

Data Index: 260973 (C4 (Web Text))

Max Activating Token Index: 956

Text #14

Max Range: 0.0328. Min Range: -0.0328

Max Act: 0.0189. Min Act: -0.0003

Data Index: 686517 (C4 (Web Text))

Max Activating Token Index: 41

Text #15

Max Range: 0.0328. Min Range: -0.0328

Max Act: 0.0185. Min Act: -0.0003

Data Index: 1109764 (C4 (Web Text))

Max Activating Token Index: 443

Text #16

Max Range: 0.0328. Min Range: -0.0328

Max Act: 0.0182. Min Act: -0.0003

Data Index: 1313183 (C4 (Web Text))

Max Activating Token Index: 793

Text #17

Max Range: 0.0328. Min Range: -0.0328

Max Act: 0.0177. Min Act: -0.0003

Data Index: 1007402 (C4 (Web Text))

Max Activating Token Index: 568

Text #18

Max Range: 0.0328. Min Range: -0.0328

Max Act: 0.0172. Min Act: -0.0003

Data Index: 200750 (C4 (Web Text))

Max Activating Token Index: 285

Text #19

Max Range: 0.0328. Min Range: -0.0328

Max Act: 0.0170. Min Act: -0.0003

Data Index: 1094699 (C4 (Web Text))

Max Activating Token Index: 651