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

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

Neuron 3454 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1440. Min Range: -0.1440

Max Act: 0.1440. Min Act: -0.0000

Data Index: 876685 (C4 (Web Text))

Max Activating Token Index: 131

Text #1

Max Range: 0.1440. Min Range: -0.1440

Max Act: 0.1269. Min Act: -0.0000

Data Index: 692318 (C4 (Web Text))

Max Activating Token Index: 389

Text #2

Max Range: 0.1440. Min Range: -0.1440

Max Act: 0.1131. Min Act: -0.0000

Data Index: 324649 (C4 (Web Text))

Max Activating Token Index: 30

Text #3

Max Range: 0.1440. Min Range: -0.1440

Max Act: 0.1198. Min Act: -0.0000

Data Index: 226180 (C4 (Web Text))

Max Activating Token Index: 21

Text #4

Max Range: 0.1440. Min Range: -0.1440

Max Act: 0.1158. Min Act: -0.0000

Data Index: 225129 (C4 (Web Text))

Max Activating Token Index: 8

Text #5

Max Range: 0.1440. Min Range: -0.1440

Max Act: 0.1130. Min Act: -0.0000

Data Index: 283318 (C4 (Web Text))

Max Activating Token Index: 371

Text #6

Max Range: 0.1440. Min Range: -0.1440

Max Act: 0.1137. Min Act: -0.0000

Data Index: 1212229 (C4 (Web Text))

Max Activating Token Index: 574

Text #7

Max Range: 0.1440. Min Range: -0.1440

Max Act: 0.1155. Min Act: -0.0000

Data Index: 1208432 (C4 (Web Text))

Max Activating Token Index: 7

Text #8

Max Range: 0.1440. Min Range: -0.1440

Max Act: 0.1156. Min Act: -0.0000

Data Index: 1063653 (C4 (Web Text))

Max Activating Token Index: 88

Text #9

Max Range: 0.1440. Min Range: -0.1440

Max Act: 0.1114. Min Act: -0.0000

Data Index: 907750 (C4 (Web Text))

Max Activating Token Index: 687

Text #10

Max Range: 0.1440. Min Range: -0.1440

Max Act: 0.1045. Min Act: -0.0000

Data Index: 545955 (C4 (Web Text))

Max Activating Token Index: 291

Text #11

Max Range: 0.1440. Min Range: -0.1440

Max Act: 0.1062. Min Act: -0.0000

Data Index: 3288 (C4 (Web Text))

Max Activating Token Index: 56

Text #12

Max Range: 0.1440. Min Range: -0.1440

Max Act: 0.1175. Min Act: -0.0000

Data Index: 621240 (C4 (Web Text))

Max Activating Token Index: 130

Text #13

Max Range: 0.1440. Min Range: -0.1440

Max Act: 0.1095. Min Act: -0.0000

Data Index: 495294 (C4 (Web Text))

Max Activating Token Index: 613

Text #14

Max Range: 0.1440. Min Range: -0.1440

Max Act: 0.1051. Min Act: -0.0000

Data Index: 77492 (C4 (Web Text))

Max Activating Token Index: 282

Text #15

Max Range: 0.1440. Min Range: -0.1440

Max Act: 0.1034. Min Act: -0.0000

Data Index: 373748 (C4 (Web Text))

Max Activating Token Index: 7

Text #16

Max Range: 0.1440. Min Range: -0.1440

Max Act: 0.1062. Min Act: -0.0000

Data Index: 1095086 (C4 (Web Text))

Max Activating Token Index: 408

Text #17

Max Range: 0.1440. Min Range: -0.1440

Max Act: 0.1016. Min Act: -0.0000

Data Index: 451628 (C4 (Web Text))

Max Activating Token Index: 971

Text #18

Max Range: 0.1440. Min Range: -0.1440

Max Act: 0.1081. Min Act: -0.0001

Data Index: 413288 (C4 (Web Text))

Max Activating Token Index: 757

Text #19

Max Range: 0.1440. Min Range: -0.1440

Max Act: 0.1057. Min Act: -0.0000

Data Index: 790556 (C4 (Web Text))

Max Activating Token Index: 335