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

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

Neuron 1135 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1261. Min Range: -0.1261

Max Act: 0.1216. Min Act: -0.0005

Data Index: 92890 (C4 (Web Text))

Max Activating Token Index: 189

Text #1

Max Range: 0.1261. Min Range: -0.1261

Max Act: 0.1261. Min Act: -0.0005

Data Index: 396988 (C4 (Web Text))

Max Activating Token Index: 337

Text #2

Max Range: 0.1261. Min Range: -0.1261

Max Act: 0.1242. Min Act: -0.0005

Data Index: 1348402 (C4 (Web Text))

Max Activating Token Index: 629

Text #3

Max Range: 0.1261. Min Range: -0.1261

Max Act: 0.1241. Min Act: -0.0005

Data Index: 1137383 (C4 (Web Text))

Max Activating Token Index: 532

Text #4

Max Range: 0.1261. Min Range: -0.1261

Max Act: 0.1201. Min Act: -0.0005

Data Index: 361636 (C4 (Web Text))

Max Activating Token Index: 335

Text #5

Max Range: 0.1261. Min Range: -0.1261

Max Act: 0.1137. Min Act: -0.0005

Data Index: 282155 (C4 (Web Text))

Max Activating Token Index: 251

Text #6

Max Range: 0.1261. Min Range: -0.1261

Max Act: 0.1170. Min Act: -0.0005

Data Index: 1358261 (C4 (Web Text))

Max Activating Token Index: 907

Text #7

Max Range: 0.1261. Min Range: -0.1261

Max Act: 0.1143. Min Act: -0.0005

Data Index: 629194 (C4 (Web Text))

Max Activating Token Index: 234

Text #8

Max Range: 0.1261. Min Range: -0.1261

Max Act: 0.1143. Min Act: -0.0005

Data Index: 795987 (C4 (Web Text))

Max Activating Token Index: 830

Text #9

Max Range: 0.1261. Min Range: -0.1261

Max Act: 0.1053. Min Act: -0.0005

Data Index: 682622 (C4 (Web Text))

Max Activating Token Index: 715

Text #10

Max Range: 0.1261. Min Range: -0.1261

Max Act: 0.1083. Min Act: -0.0005

Data Index: 706303 (C4 (Web Text))

Max Activating Token Index: 409

Text #11

Max Range: 0.1261. Min Range: -0.1261

Max Act: 0.1117. Min Act: -0.0005

Data Index: 280868 (C4 (Web Text))

Max Activating Token Index: 179

Text #12

Max Range: 0.1261. Min Range: -0.1261

Max Act: 0.1097. Min Act: -0.0005

Data Index: 305584 (C4 (Web Text))

Max Activating Token Index: 1011

Text #13

Max Range: 0.1261. Min Range: -0.1261

Max Act: 0.1184. Min Act: -0.0005

Data Index: 72209 (C4 (Web Text))

Max Activating Token Index: 822

Text #14

Max Range: 0.1261. Min Range: -0.1261

Max Act: 0.1085. Min Act: -0.0005

Data Index: 1037876 (C4 (Web Text))

Max Activating Token Index: 343

Text #15

Max Range: 0.1261. Min Range: -0.1261

Max Act: 0.1087. Min Act: -0.0005

Data Index: 11120 (C4 (Web Text))

Max Activating Token Index: 109

Text #16

Max Range: 0.1261. Min Range: -0.1261

Max Act: 0.1161. Min Act: -0.0005

Data Index: 388996 (C4 (Web Text))

Max Activating Token Index: 299

Text #17

Max Range: 0.1261. Min Range: -0.1261

Max Act: 0.1007. Min Act: -0.0005

Data Index: 605820 (C4 (Web Text))

Max Activating Token Index: 801

Text #18

Max Range: 0.1261. Min Range: -0.1261

Max Act: 0.1037. Min Act: -0.0005

Data Index: 688185 (C4 (Web Text))

Max Activating Token Index: 1008

Text #19

Max Range: 0.1261. Min Range: -0.1261

Max Act: 0.0974. Min Act: -0.0005

Data Index: 68656 (C4 (Web Text))

Max Activating Token Index: 575