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

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

Neuron 747 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1296. Min Range: -0.1296

Max Act: 0.1296. Min Act: -0.0006

Data Index: 341757 (C4 (Web Text))

Max Activating Token Index: 140

Text #1

Max Range: 0.1296. Min Range: -0.1296

Max Act: 0.1231. Min Act: -0.0006

Data Index: 905578 (C4 (Web Text))

Max Activating Token Index: 985

Text #2

Max Range: 0.1296. Min Range: -0.1296

Max Act: 0.1214. Min Act: -0.0006

Data Index: 322714 (C4 (Web Text))

Max Activating Token Index: 598

Text #3

Max Range: 0.1296. Min Range: -0.1296

Max Act: 0.1256. Min Act: -0.0006

Data Index: 798770 (C4 (Web Text))

Max Activating Token Index: 832

Text #4

Max Range: 0.1296. Min Range: -0.1296

Max Act: 0.1198. Min Act: -0.0006

Data Index: 727637 (C4 (Web Text))

Max Activating Token Index: 124

Text #5

Max Range: 0.1296. Min Range: -0.1296

Max Act: 0.1195. Min Act: -0.0006

Data Index: 926667 (C4 (Web Text))

Max Activating Token Index: 756

Text #6

Max Range: 0.1296. Min Range: -0.1296

Max Act: 0.1158. Min Act: -0.0006

Data Index: 365266 (C4 (Web Text))

Max Activating Token Index: 182

Text #7

Max Range: 0.1296. Min Range: -0.1296

Max Act: 0.1192. Min Act: -0.0006

Data Index: 546871 (C4 (Web Text))

Max Activating Token Index: 237

Text #8

Max Range: 0.1296. Min Range: -0.1296

Max Act: 0.1146. Min Act: -0.0006

Data Index: 672708 (C4 (Web Text))

Max Activating Token Index: 797

Text #9

Max Range: 0.1296. Min Range: -0.1296

Max Act: 0.1179. Min Act: -0.0006

Data Index: 208261 (C4 (Web Text))

Max Activating Token Index: 145

Text #10

Max Range: 0.1296. Min Range: -0.1296

Max Act: 0.1175. Min Act: -0.0006

Data Index: 1107713 (C4 (Web Text))

Max Activating Token Index: 871

Text #11

Max Range: 0.1296. Min Range: -0.1296

Max Act: 0.1125. Min Act: -0.0006

Data Index: 98821 (C4 (Web Text))

Max Activating Token Index: 743

Text #12

Max Range: 0.1296. Min Range: -0.1296

Max Act: 0.1123. Min Act: -0.0006

Data Index: 1325271 (C4 (Web Text))

Max Activating Token Index: 823

Text #13

Max Range: 0.1296. Min Range: -0.1296

Max Act: 0.1116. Min Act: -0.0006

Data Index: 441367 (C4 (Web Text))

Max Activating Token Index: 137

Text #14

Max Range: 0.1296. Min Range: -0.1296

Max Act: 0.1111. Min Act: -0.0006

Data Index: 212071 (C4 (Web Text))

Max Activating Token Index: 539

Text #15

Max Range: 0.1296. Min Range: -0.1296

Max Act: 0.1152. Min Act: -0.0006

Data Index: 1263589 (C4 (Web Text))

Max Activating Token Index: 837

Text #16

Max Range: 0.1296. Min Range: -0.1296

Max Act: 0.1137. Min Act: -0.0006

Data Index: 647196 (C4 (Web Text))

Max Activating Token Index: 708

Text #17

Max Range: 0.1296. Min Range: -0.1296

Max Act: 0.1087. Min Act: -0.0006

Data Index: 1359522 (C4 (Web Text))

Max Activating Token Index: 825

Text #18

Max Range: 0.1296. Min Range: -0.1296

Max Act: 0.1047. Min Act: -0.0006

Data Index: 429159 (C4 (Web Text))

Max Activating Token Index: 921

Text #19

Max Range: 0.1296. Min Range: -0.1296

Max Act: 0.1076. Min Act: -0.0006

Data Index: 144514 (C4 (Web Text))

Max Activating Token Index: 323