Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2968 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1316. Min Range: -0.1316

Max Act: 0.1300. Min Act: -0.0001

Data Index: 88137 (C4 (Web Text))

Max Activating Token Index: 33

Text #1

Max Range: 0.1316. Min Range: -0.1316

Max Act: 0.1294. Min Act: -0.0001

Data Index: 638006 (C4 (Web Text))

Max Activating Token Index: 51

Text #2

Max Range: 0.1316. Min Range: -0.1316

Max Act: 0.1316. Min Act: -0.0001

Data Index: 1256371 (C4 (Web Text))

Max Activating Token Index: 552

Text #3

Max Range: 0.1316. Min Range: -0.1316

Max Act: 0.1196. Min Act: -0.0001

Data Index: 113961 (C4 (Web Text))

Max Activating Token Index: 356

Text #4

Max Range: 0.1316. Min Range: -0.1316

Max Act: 0.1295. Min Act: -0.0001

Data Index: 1061552 (C4 (Web Text))

Max Activating Token Index: 872

Text #5

Max Range: 0.1316. Min Range: -0.1316

Max Act: 0.1224. Min Act: -0.0001

Data Index: 1199497 (C4 (Web Text))

Max Activating Token Index: 876

Text #6

Max Range: 0.1316. Min Range: -0.1316

Max Act: 0.1168. Min Act: -0.0001

Data Index: 1304564 (C4 (Web Text))

Max Activating Token Index: 241

Text #7

Max Range: 0.1316. Min Range: -0.1316

Max Act: 0.1200. Min Act: -0.0001

Data Index: 331252 (C4 (Web Text))

Max Activating Token Index: 433

Text #8

Max Range: 0.1316. Min Range: -0.1316

Max Act: 0.1156. Min Act: -0.0001

Data Index: 1055630 (C4 (Web Text))

Max Activating Token Index: 178

Text #9

Max Range: 0.1316. Min Range: -0.1316

Max Act: 0.1194. Min Act: -0.0001

Data Index: 595014 (C4 (Web Text))

Max Activating Token Index: 735

Text #10

Max Range: 0.1316. Min Range: -0.1316

Max Act: 0.1237. Min Act: -0.0001

Data Index: 324924 (C4 (Web Text))

Max Activating Token Index: 132

Text #11

Max Range: 0.1316. Min Range: -0.1316

Max Act: 0.1172. Min Act: -0.0001

Data Index: 1138465 (C4 (Web Text))

Max Activating Token Index: 947

Text #12

Max Range: 0.1316. Min Range: -0.1316

Max Act: 0.1174. Min Act: -0.0001

Data Index: 1120702 (C4 (Web Text))

Max Activating Token Index: 1000

Text #13

Max Range: 0.1316. Min Range: -0.1316

Max Act: 0.1120. Min Act: -0.0001

Data Index: 82123 (C4 (Web Text))

Max Activating Token Index: 776

Text #14

Max Range: 0.1316. Min Range: -0.1316

Max Act: 0.1127. Min Act: -0.0001

Data Index: 265063 (C4 (Web Text))

Max Activating Token Index: 546

Text #15

Max Range: 0.1316. Min Range: -0.1316

Max Act: 0.1128. Min Act: 0.0002

Data Index: 869348 (C4 (Web Text))

Max Activating Token Index: 55

Text #16

Max Range: 0.1316. Min Range: -0.1316

Max Act: 0.1125. Min Act: -0.0001

Data Index: 5870 (C4 (Web Text))

Max Activating Token Index: 624

Text #17

Max Range: 0.1316. Min Range: -0.1316

Max Act: 0.1078. Min Act: -0.0001

Data Index: 661666 (C4 (Web Text))

Max Activating Token Index: 782

Text #18

Max Range: 0.1316. Min Range: -0.1316

Max Act: 0.1164. Min Act: -0.0001

Data Index: 224218 (C4 (Web Text))

Max Activating Token Index: 326

Text #19

Max Range: 0.1316. Min Range: -0.1316

Max Act: 0.1071. Min Act: -0.0001

Data Index: 489570 (C4 (Web Text))

Max Activating Token Index: 430