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

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

Neuron 594 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: 0.1392. Min Range: -0.1392

Max Act: 0.1392. Min Act: -0.0003

Data Index: 1099746 (C4 (Web Text))

Max Activating Token Index: 41

Text #1

Max Range: 0.1392. Min Range: -0.1392

Max Act: 0.1241. Min Act: -0.0003

Data Index: 1147426 (C4 (Web Text))

Max Activating Token Index: 129

Text #2

Max Range: 0.1392. Min Range: -0.1392

Max Act: 0.1188. Min Act: -0.0002

Data Index: 914981 (C4 (Web Text))

Max Activating Token Index: 334

Text #3

Max Range: 0.1392. Min Range: -0.1392

Max Act: 0.1190. Min Act: -0.0003

Data Index: 1077612 (C4 (Web Text))

Max Activating Token Index: 6

Text #4

Max Range: 0.1392. Min Range: -0.1392

Max Act: 0.1213. Min Act: -0.0003

Data Index: 873224 (C4 (Web Text))

Max Activating Token Index: 250

Text #5

Max Range: 0.1392. Min Range: -0.1392

Max Act: 0.1156. Min Act: -0.0002

Data Index: 902711 (C4 (Web Text))

Max Activating Token Index: 222

Text #6

Max Range: 0.1392. Min Range: -0.1392

Max Act: 0.1096. Min Act: -0.0003

Data Index: 1178096 (C4 (Web Text))

Max Activating Token Index: 365

Text #7

Max Range: 0.1392. Min Range: -0.1392

Max Act: 0.1139. Min Act: -0.0003

Data Index: 541982 (C4 (Web Text))

Max Activating Token Index: 264

Text #8

Max Range: 0.1392. Min Range: -0.1392

Max Act: 0.1126. Min Act: -0.0003

Data Index: 1148640 (C4 (Web Text))

Max Activating Token Index: 204

Text #9

Max Range: 0.1392. Min Range: -0.1392

Max Act: 0.1125. Min Act: -0.0003

Data Index: 411030 (C4 (Web Text))

Max Activating Token Index: 193

Text #10

Max Range: 0.1392. Min Range: -0.1392

Max Act: 0.1120. Min Act: -0.0003

Data Index: 884256 (C4 (Web Text))

Max Activating Token Index: 691

Text #11

Max Range: 0.1392. Min Range: -0.1392

Max Act: 0.1083. Min Act: -0.0003

Data Index: 193049 (C4 (Web Text))

Max Activating Token Index: 171

Text #12

Max Range: 0.1392. Min Range: -0.1392

Max Act: 0.1067. Min Act: -0.0003

Data Index: 40307 (C4 (Web Text))

Max Activating Token Index: 792

Text #13

Max Range: 0.1392. Min Range: -0.1392

Max Act: 0.1143. Min Act: -0.0002

Data Index: 713271 (C4 (Web Text))

Max Activating Token Index: 838

Text #14

Max Range: 0.1392. Min Range: -0.1392

Max Act: 0.1106. Min Act: -0.0003

Data Index: 818728 (C4 (Web Text))

Max Activating Token Index: 82

Text #15

Max Range: 0.1392. Min Range: -0.1392

Max Act: 0.1096. Min Act: -0.0003

Data Index: 1217133 (C4 (Web Text))

Max Activating Token Index: 572

Text #16

Max Range: 0.1392. Min Range: -0.1392

Max Act: 0.1087. Min Act: -0.0003

Data Index: 969125 (C4 (Web Text))

Max Activating Token Index: 406

Text #17

Max Range: 0.1392. Min Range: -0.1392

Max Act: 0.1079. Min Act: -0.0003

Data Index: 80505 (C4 (Web Text))

Max Activating Token Index: 383

Text #18

Max Range: 0.1392. Min Range: -0.1392

Max Act: 0.1079. Min Act: -0.0002

Data Index: 462647 (C4 (Web Text))

Max Activating Token Index: 934

Text #19

Max Range: 0.1392. Min Range: -0.1392

Max Act: 0.1073. Min Act: -0.0003

Data Index: 1243566 (C4 (Web Text))

Max Activating Token Index: 758