Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2635 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1328. Min Range: -0.1328

Max Act: 0.1276. Min Act: -0.0000

Data Index: 821432 (C4 (Web Text))

Max Activating Token Index: 419

Text #1

Max Range: 0.1328. Min Range: -0.1328

Max Act: 0.1328. Min Act: -0.0000

Data Index: 1124400 (C4 (Web Text))

Max Activating Token Index: 936

Text #2

Max Range: 0.1328. Min Range: -0.1328

Max Act: 0.1256. Min Act: -0.0001

Data Index: 1009377 (C4 (Web Text))

Max Activating Token Index: 796

Text #3

Max Range: 0.1328. Min Range: -0.1328

Max Act: 0.1200. Min Act: -0.0000

Data Index: 1096049 (C4 (Web Text))

Max Activating Token Index: 238

Text #4

Max Range: 0.1328. Min Range: -0.1328

Max Act: 0.1220. Min Act: -0.0001

Data Index: 231069 (C4 (Web Text))

Max Activating Token Index: 327

Text #5

Max Range: 0.1328. Min Range: -0.1328

Max Act: 0.1256. Min Act: -0.0001

Data Index: 267454 (C4 (Web Text))

Max Activating Token Index: 644

Text #6

Max Range: 0.1328. Min Range: -0.1328

Max Act: 0.1204. Min Act: -0.0000

Data Index: 24902 (C4 (Web Text))

Max Activating Token Index: 920

Text #7

Max Range: 0.1328. Min Range: -0.1328

Max Act: 0.1142. Min Act: -0.0000

Data Index: 256705 (C4 (Web Text))

Max Activating Token Index: 205

Text #8

Max Range: 0.1328. Min Range: -0.1328

Max Act: 0.1167. Min Act: -0.0000

Data Index: 524843 (C4 (Web Text))

Max Activating Token Index: 359

Text #9

Max Range: 0.1328. Min Range: -0.1328

Max Act: 0.1229. Min Act: -0.0001

Data Index: 850854 (C4 (Web Text))

Max Activating Token Index: 481

Text #10

Max Range: 0.1328. Min Range: -0.1328

Max Act: 0.1148. Min Act: -0.0000

Data Index: 1171827 (C4 (Web Text))

Max Activating Token Index: 402

Text #11

Max Range: 0.1328. Min Range: -0.1328

Max Act: 0.1227. Min Act: -0.0000

Data Index: 182675 (C4 (Web Text))

Max Activating Token Index: 512

Text #12

Max Range: 0.1328. Min Range: -0.1328

Max Act: 0.1186. Min Act: -0.0001

Data Index: 526221 (C4 (Web Text))

Max Activating Token Index: 483

Text #13

Max Range: 0.1328. Min Range: -0.1328

Max Act: 0.1169. Min Act: -0.0000

Data Index: 1060295 (C4 (Web Text))

Max Activating Token Index: 918

Text #14

Max Range: 0.1328. Min Range: -0.1328

Max Act: 0.1120. Min Act: -0.0001

Data Index: 27979 (C4 (Web Text))

Max Activating Token Index: 334

Text #15

Max Range: 0.1328. Min Range: -0.1328

Max Act: 0.1034. Min Act: -0.0001

Data Index: 1352750 (C4 (Web Text))

Max Activating Token Index: 83

Text #16

Max Range: 0.1328. Min Range: -0.1328

Max Act: 0.1079. Min Act: -0.0000

Data Index: 823237 (C4 (Web Text))

Max Activating Token Index: 135

Text #17

Max Range: 0.1328. Min Range: -0.1328

Max Act: 0.1099. Min Act: -0.0000

Data Index: 1150867 (C4 (Web Text))

Max Activating Token Index: 101

Text #18

Max Range: 0.1328. Min Range: -0.1328

Max Act: 0.1042. Min Act: -0.0001

Data Index: 696107 (C4 (Web Text))

Max Activating Token Index: 133

Text #19

Max Range: 0.1328. Min Range: -0.1328

Max Act: 0.1039. Min Act: -0.0001

Data Index: 434653 (C4 (Web Text))

Max Activating Token Index: 954