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

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

Neuron 1807 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: 0.1218. Min Range: -0.1218

Max Act: 0.1181. Min Act: -0.0002

Data Index: 748748 (C4 (Web Text))

Max Activating Token Index: 826

Text #1

Max Range: 0.1218. Min Range: -0.1218

Max Act: 0.1218. Min Act: -0.0002

Data Index: 158605 (C4 (Web Text))

Max Activating Token Index: 882

Text #2

Max Range: 0.1218. Min Range: -0.1218

Max Act: 0.1094. Min Act: -0.0002

Data Index: 1269106 (C4 (Web Text))

Max Activating Token Index: 835

Text #3

Max Range: 0.1218. Min Range: -0.1218

Max Act: 0.1138. Min Act: -0.0002

Data Index: 819087 (C4 (Web Text))

Max Activating Token Index: 116

Text #4

Max Range: 0.1218. Min Range: -0.1218

Max Act: 0.1127. Min Act: -0.0002

Data Index: 992581 (C4 (Web Text))

Max Activating Token Index: 467

Text #5

Max Range: 0.1218. Min Range: -0.1218

Max Act: 0.1167. Min Act: -0.0002

Data Index: 321982 (C4 (Web Text))

Max Activating Token Index: 909

Text #6

Max Range: 0.1218. Min Range: -0.1218

Max Act: 0.1121. Min Act: -0.0002

Data Index: 805393 (C4 (Web Text))

Max Activating Token Index: 927

Text #7

Max Range: 0.1218. Min Range: -0.1218

Max Act: 0.1170. Min Act: -0.0002

Data Index: 894464 (C4 (Web Text))

Max Activating Token Index: 251

Text #8

Max Range: 0.1218. Min Range: -0.1218

Max Act: 0.1103. Min Act: -0.0002

Data Index: 252002 (C4 (Web Text))

Max Activating Token Index: 834

Text #9

Max Range: 0.1218. Min Range: -0.1218

Max Act: 0.1140. Min Act: -0.0002

Data Index: 702595 (C4 (Web Text))

Max Activating Token Index: 837

Text #10

Max Range: 0.1218. Min Range: -0.1218

Max Act: 0.1127. Min Act: -0.0002

Data Index: 92427 (C4 (Web Text))

Max Activating Token Index: 119

Text #11

Max Range: 0.1218. Min Range: -0.1218

Max Act: 0.1162. Min Act: -0.0002

Data Index: 1027339 (C4 (Web Text))

Max Activating Token Index: 723

Text #12

Max Range: 0.1218. Min Range: -0.1218

Max Act: 0.1043. Min Act: -0.0002

Data Index: 80646 (C4 (Web Text))

Max Activating Token Index: 91

Text #13

Max Range: 0.1218. Min Range: -0.1218

Max Act: 0.1040. Min Act: -0.0002

Data Index: 1200166 (C4 (Web Text))

Max Activating Token Index: 896

Text #14

Max Range: 0.1218. Min Range: -0.1218

Max Act: 0.1055. Min Act: -0.0002

Data Index: 559228 (C4 (Web Text))

Max Activating Token Index: 569

Text #15

Max Range: 0.1218. Min Range: -0.1218

Max Act: 0.1074. Min Act: -0.0002

Data Index: 633897 (C4 (Web Text))

Max Activating Token Index: 278

Text #16

Max Range: 0.1218. Min Range: -0.1218

Max Act: 0.1047. Min Act: -0.0002

Data Index: 517799 (C4 (Web Text))

Max Activating Token Index: 867

Text #17

Max Range: 0.1218. Min Range: -0.1218

Max Act: 0.1028. Min Act: -0.0002

Data Index: 748330 (C4 (Web Text))

Max Activating Token Index: 993

Text #18

Max Range: 0.1218. Min Range: -0.1218

Max Act: 0.0992. Min Act: -0.0002

Data Index: 822652 (C4 (Web Text))

Max Activating Token Index: 854

Text #19

Max Range: 0.1218. Min Range: -0.1218

Max Act: 0.1061. Min Act: -0.0002

Data Index: 736263 (C4 (Web Text))

Max Activating Token Index: 999