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

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

Neuron 4762 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: 0.1249. Min Range: -0.1249

Max Act: 0.1247. Min Act: -0.0003

Data Index: 222240 (C4 (Web Text))

Max Activating Token Index: 291

Text #1

Max Range: 0.1249. Min Range: -0.1249

Max Act: 0.1249. Min Act: -0.0002

Data Index: 10451 (C4 (Web Text))

Max Activating Token Index: 208

Text #2

Max Range: 0.1249. Min Range: -0.1249

Max Act: 0.1195. Min Act: -0.0003

Data Index: 60697 (C4 (Web Text))

Max Activating Token Index: 292

Text #3

Max Range: 0.1249. Min Range: -0.1249

Max Act: 0.1227. Min Act: -0.0002

Data Index: 218304 (C4 (Web Text))

Max Activating Token Index: 496

Text #4

Max Range: 0.1249. Min Range: -0.1249

Max Act: 0.1223. Min Act: -0.0003

Data Index: 1104583 (C4 (Web Text))

Max Activating Token Index: 286

Text #5

Max Range: 0.1249. Min Range: -0.1249

Max Act: 0.1223. Min Act: -0.0002

Data Index: 812531 (C4 (Web Text))

Max Activating Token Index: 186

Text #6

Max Range: 0.1249. Min Range: -0.1249

Max Act: 0.1200. Min Act: -0.0002

Data Index: 812258 (C4 (Web Text))

Max Activating Token Index: 294

Text #7

Max Range: 0.1249. Min Range: -0.1249

Max Act: 0.1191. Min Act: -0.0003

Data Index: 1264446 (C4 (Web Text))

Max Activating Token Index: 509

Text #8

Max Range: 0.1249. Min Range: -0.1249

Max Act: 0.1104. Min Act: -0.0002

Data Index: 575830 (C4 (Web Text))

Max Activating Token Index: 333

Text #9

Max Range: 0.1249. Min Range: -0.1249

Max Act: 0.1062. Min Act: -0.0002

Data Index: 119576 (C4 (Web Text))

Max Activating Token Index: 208

Text #10

Max Range: 0.1249. Min Range: -0.1249

Max Act: 0.1044. Min Act: -0.0002

Data Index: 1343379 (C4 (Web Text))

Max Activating Token Index: 222

Text #11

Max Range: 0.1249. Min Range: -0.1249

Max Act: 0.1091. Min Act: -0.0002

Data Index: 434948 (C4 (Web Text))

Max Activating Token Index: 147

Text #12

Max Range: 0.1249. Min Range: -0.1249

Max Act: 0.1053. Min Act: -0.0003

Data Index: 302792 (C4 (Web Text))

Max Activating Token Index: 126

Text #13

Max Range: 0.1249. Min Range: -0.1249

Max Act: 0.1070. Min Act: -0.0002

Data Index: 503386 (C4 (Web Text))

Max Activating Token Index: 225

Text #14

Max Range: 0.1249. Min Range: -0.1249

Max Act: 0.1065. Min Act: -0.0003

Data Index: 897009 (C4 (Web Text))

Max Activating Token Index: 460

Text #15

Max Range: 0.1249. Min Range: -0.1249

Max Act: 0.1108. Min Act: -0.0002

Data Index: 1061556 (C4 (Web Text))

Max Activating Token Index: 447

Text #16

Max Range: 0.1249. Min Range: -0.1249

Max Act: 0.1073. Min Act: -0.0002

Data Index: 204269 (C4 (Web Text))

Max Activating Token Index: 112

Text #17

Max Range: 0.1249. Min Range: -0.1249

Max Act: 0.1105. Min Act: -0.0003

Data Index: 389253 (C4 (Web Text))

Max Activating Token Index: 301

Text #18

Max Range: 0.1249. Min Range: -0.1249

Max Act: 0.1108. Min Act: -0.0002

Data Index: 113825 (C4 (Web Text))

Max Activating Token Index: 404

Text #19

Max Range: 0.1249. Min Range: -0.1249

Max Act: 0.1089. Min Act: -0.0003

Data Index: 291507 (C4 (Web Text))

Max Activating Token Index: 25