Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1372 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1422. Min Range: -0.1422

Max Act: 0.1422. Min Act: -0.0001

Data Index: 696699 (C4 (Web Text))

Max Activating Token Index: 79

Text #1

Max Range: 0.1422. Min Range: -0.1422

Max Act: 0.1256. Min Act: -0.0002

Data Index: 296048 (C4 (Web Text))

Max Activating Token Index: 185

Text #2

Max Range: 0.1422. Min Range: -0.1422

Max Act: 0.1278. Min Act: -0.0002

Data Index: 1026827 (C4 (Web Text))

Max Activating Token Index: 652

Text #3

Max Range: 0.1422. Min Range: -0.1422

Max Act: 0.1231. Min Act: -0.0002

Data Index: 1211076 (C4 (Web Text))

Max Activating Token Index: 480

Text #4

Max Range: 0.1422. Min Range: -0.1422

Max Act: 0.1204. Min Act: -0.0002

Data Index: 1032675 (C4 (Web Text))

Max Activating Token Index: 119

Text #5

Max Range: 0.1422. Min Range: -0.1422

Max Act: 0.1216. Min Act: -0.0002

Data Index: 657184 (C4 (Web Text))

Max Activating Token Index: 32

Text #6

Max Range: 0.1422. Min Range: -0.1422

Max Act: 0.1228. Min Act: -0.0002

Data Index: 639449 (C4 (Web Text))

Max Activating Token Index: 26

Text #7

Max Range: 0.1422. Min Range: -0.1422

Max Act: 0.1098. Min Act: -0.0002

Data Index: 514059 (C4 (Web Text))

Max Activating Token Index: 688

Text #8

Max Range: 0.1422. Min Range: -0.1422

Max Act: 0.1203. Min Act: -0.0002

Data Index: 154391 (C4 (Web Text))

Max Activating Token Index: 9

Text #9

Max Range: 0.1422. Min Range: -0.1422

Max Act: 0.1219. Min Act: -0.0002

Data Index: 273836 (C4 (Web Text))

Max Activating Token Index: 410

Text #10

Max Range: 0.1422. Min Range: -0.1422

Max Act: 0.1180. Min Act: -0.0002

Data Index: 481190 (C4 (Web Text))

Max Activating Token Index: 489

Text #11

Max Range: 0.1422. Min Range: -0.1422

Max Act: 0.1177. Min Act: -0.0002

Data Index: 677422 (C4 (Web Text))

Max Activating Token Index: 358

Text #12

Max Range: 0.1422. Min Range: -0.1422

Max Act: 0.1172. Min Act: -0.0002

Data Index: 1055862 (C4 (Web Text))

Max Activating Token Index: 345

Text #13

Max Range: 0.1422. Min Range: -0.1422

Max Act: 0.1129. Min Act: -0.0002

Data Index: 1315251 (C4 (Web Text))

Max Activating Token Index: 1019

Text #14

Max Range: 0.1422. Min Range: -0.1422

Max Act: 0.1130. Min Act: -0.0002

Data Index: 746324 (C4 (Web Text))

Max Activating Token Index: 174

Text #15

Max Range: 0.1422. Min Range: -0.1422

Max Act: 0.1155. Min Act: -0.0002

Data Index: 943104 (C4 (Web Text))

Max Activating Token Index: 330

Text #16

Max Range: 0.1422. Min Range: -0.1422

Max Act: 0.1146. Min Act: -0.0002

Data Index: 1055334 (C4 (Web Text))

Max Activating Token Index: 59

Text #17

Max Range: 0.1422. Min Range: -0.1422

Max Act: 0.1116. Min Act: -0.0002

Data Index: 580153 (C4 (Web Text))

Max Activating Token Index: 61

Text #18

Max Range: 0.1422. Min Range: -0.1422

Max Act: 0.1144. Min Act: -0.0002

Data Index: 583734 (C4 (Web Text))

Max Activating Token Index: 185

Text #19

Max Range: 0.1422. Min Range: -0.1422

Max Act: 0.1189. Min Act: -0.0002

Data Index: 640425 (C4 (Web Text))

Max Activating Token Index: 425