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

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

Neuron 3746 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0307. Min Range: -0.0307

Max Act: 0.0307. Min Act: -0.0002

Data Index: 1076874 (C4 (Web Text))

Max Activating Token Index: 52

Text #1

Max Range: 0.0307. Min Range: -0.0307

Max Act: 0.0179. Min Act: -0.0002

Data Index: 395910 (C4 (Web Text))

Max Activating Token Index: 234

Text #2

Max Range: 0.0307. Min Range: -0.0307

Max Act: 0.0191. Min Act: -0.0002

Data Index: 345991 (C4 (Web Text))

Max Activating Token Index: 530

Text #3

Max Range: 0.0307. Min Range: -0.0307

Max Act: 0.0212. Min Act: -0.0002

Data Index: 713628 (C4 (Web Text))

Max Activating Token Index: 428

Text #4

Max Range: 0.0307. Min Range: -0.0307

Max Act: 0.0218. Min Act: -0.0002

Data Index: 1033765 (C4 (Web Text))

Max Activating Token Index: 173

Text #5

Max Range: 0.0307. Min Range: -0.0307

Max Act: 0.0184. Min Act: -0.0002

Data Index: 1314340 (C4 (Web Text))

Max Activating Token Index: 545

Text #6

Max Range: 0.0307. Min Range: -0.0307

Max Act: 0.0162. Min Act: -0.0002

Data Index: 1250870 (C4 (Web Text))

Max Activating Token Index: 142

Text #7

Max Range: 0.0307. Min Range: -0.0307

Max Act: 0.0169. Min Act: -0.0002

Data Index: 1069985 (C4 (Web Text))

Max Activating Token Index: 183

Text #8

Max Range: 0.0307. Min Range: -0.0307

Max Act: 0.0178. Min Act: -0.0002

Data Index: 7918 (C4 (Web Text))

Max Activating Token Index: 373

Text #9

Max Range: 0.0307. Min Range: -0.0307

Max Act: 0.0175. Min Act: -0.0002

Data Index: 767480 (C4 (Web Text))

Max Activating Token Index: 61

Text #10

Max Range: 0.0307. Min Range: -0.0307

Max Act: 0.0159. Min Act: -0.0002

Data Index: 1010969 (C4 (Web Text))

Max Activating Token Index: 125

Text #11

Max Range: 0.0307. Min Range: -0.0307

Max Act: 0.0186. Min Act: -0.0002

Data Index: 762410 (C4 (Web Text))

Max Activating Token Index: 532

Text #12

Max Range: 0.0307. Min Range: -0.0307

Max Act: 0.0167. Min Act: -0.0002

Data Index: 757281 (C4 (Web Text))

Max Activating Token Index: 980

Text #13

Max Range: 0.0307. Min Range: -0.0307

Max Act: 0.0187. Min Act: -0.0002

Data Index: 974047 (C4 (Web Text))

Max Activating Token Index: 411

Text #14

Max Range: 0.0307. Min Range: -0.0307

Max Act: 0.0174. Min Act: -0.0002

Data Index: 547045 (C4 (Web Text))

Max Activating Token Index: 1015

Text #15

Max Range: 0.0307. Min Range: -0.0307

Max Act: 0.0165. Min Act: -0.0002

Data Index: 749162 (C4 (Web Text))

Max Activating Token Index: 1014

Text #16

Max Range: 0.0307. Min Range: -0.0307

Max Act: 0.0164. Min Act: -0.0002

Data Index: 1199958 (C4 (Web Text))

Max Activating Token Index: 396

Text #17

Max Range: 0.0307. Min Range: -0.0307

Max Act: 0.0118. Min Act: -0.0002

Data Index: 606587 (C4 (Web Text))

Max Activating Token Index: 844

Text #18

Max Range: 0.0307. Min Range: -0.0307

Max Act: 0.0163. Min Act: -0.0002

Data Index: 831172 (C4 (Web Text))

Max Activating Token Index: 32

Text #19

Max Range: 0.0307. Min Range: -0.0307

Max Act: 0.0148. Min Act: -0.0002

Data Index: 880898 (C4 (Web Text))

Max Activating Token Index: 294