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

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

Neuron 586 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1160. Min Range: -0.1160

Max Act: 0.1160. Min Act: -0.0002

Data Index: 87594 (C4 (Web Text))

Max Activating Token Index: 288

Text #1

Max Range: 0.1160. Min Range: -0.1160

Max Act: 0.1064. Min Act: -0.0002

Data Index: 405043 (C4 (Web Text))

Max Activating Token Index: 171

Text #2

Max Range: 0.1160. Min Range: -0.1160

Max Act: 0.1147. Min Act: -0.0002

Data Index: 406022 (C4 (Web Text))

Max Activating Token Index: 419

Text #3

Max Range: 0.1160. Min Range: -0.1160

Max Act: 0.1148. Min Act: -0.0002

Data Index: 735669 (C4 (Web Text))

Max Activating Token Index: 386

Text #4

Max Range: 0.1160. Min Range: -0.1160

Max Act: 0.1144. Min Act: -0.0002

Data Index: 993871 (C4 (Web Text))

Max Activating Token Index: 396

Text #5

Max Range: 0.1160. Min Range: -0.1160

Max Act: 0.1150. Min Act: -0.0002

Data Index: 1179628 (C4 (Web Text))

Max Activating Token Index: 386

Text #6

Max Range: 0.1160. Min Range: -0.1160

Max Act: 0.1149. Min Act: -0.0002

Data Index: 681969 (C4 (Web Text))

Max Activating Token Index: 490

Text #7

Max Range: 0.1160. Min Range: -0.1160

Max Act: 0.1133. Min Act: -0.0002

Data Index: 410067 (C4 (Web Text))

Max Activating Token Index: 424

Text #8

Max Range: 0.1160. Min Range: -0.1160

Max Act: 0.1149. Min Act: -0.0002

Data Index: 15564 (C4 (Web Text))

Max Activating Token Index: 448

Text #9

Max Range: 0.1160. Min Range: -0.1160

Max Act: 0.1143. Min Act: -0.0002

Data Index: 1297538 (C4 (Web Text))

Max Activating Token Index: 364

Text #10

Max Range: 0.1160. Min Range: -0.1160

Max Act: 0.1140. Min Act: -0.0002

Data Index: 96497 (C4 (Web Text))

Max Activating Token Index: 337

Text #11

Max Range: 0.1160. Min Range: -0.1160

Max Act: 0.1145. Min Act: -0.0002

Data Index: 677650 (C4 (Web Text))

Max Activating Token Index: 427

Text #12

Max Range: 0.1160. Min Range: -0.1160

Max Act: 0.1134. Min Act: -0.0002

Data Index: 167304 (C4 (Web Text))

Max Activating Token Index: 151

Text #13

Max Range: 0.1160. Min Range: -0.1160

Max Act: 0.1150. Min Act: -0.0002

Data Index: 651279 (C4 (Web Text))

Max Activating Token Index: 99

Text #14

Max Range: 0.1160. Min Range: -0.1160

Max Act: 0.1139. Min Act: -0.0002

Data Index: 1208092 (C4 (Web Text))

Max Activating Token Index: 422

Text #15

Max Range: 0.1160. Min Range: -0.1160

Max Act: 0.1127. Min Act: -0.0002

Data Index: 1148993 (C4 (Web Text))

Max Activating Token Index: 315

Text #16

Max Range: 0.1160. Min Range: -0.1160

Max Act: 0.1126. Min Act: -0.0002

Data Index: 947797 (C4 (Web Text))

Max Activating Token Index: 431

Text #17

Max Range: 0.1160. Min Range: -0.1160

Max Act: 0.1128. Min Act: -0.0002

Data Index: 865619 (C4 (Web Text))

Max Activating Token Index: 259

Text #18

Max Range: 0.1160. Min Range: -0.1160

Max Act: 0.1133. Min Act: -0.0002

Data Index: 1008573 (C4 (Web Text))

Max Activating Token Index: 432

Text #19

Max Range: 0.1160. Min Range: -0.1160

Max Act: 0.1132. Min Act: -0.0002

Data Index: 852715 (C4 (Web Text))

Max Activating Token Index: 422