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

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

Neuron 708 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1138. Min Range: -0.1138

Max Act: 0.1121. Min Act: -0.0004

Data Index: 347050 (C4 (Web Text))

Max Activating Token Index: 974

Text #1

Max Range: 0.1138. Min Range: -0.1138

Max Act: 0.1138. Min Act: -0.0004

Data Index: 1053986 (C4 (Web Text))

Max Activating Token Index: 987

Text #2

Max Range: 0.1138. Min Range: -0.1138

Max Act: 0.0941. Min Act: -0.0004

Data Index: 1310407 (C4 (Web Text))

Max Activating Token Index: 676

Text #3

Max Range: 0.1138. Min Range: -0.1138

Max Act: 0.0916. Min Act: -0.0004

Data Index: 805330 (C4 (Web Text))

Max Activating Token Index: 838

Text #4

Max Range: 0.1138. Min Range: -0.1138

Max Act: 0.1032. Min Act: -0.0004

Data Index: 574809 (C4 (Web Text))

Max Activating Token Index: 204

Text #5

Max Range: 0.1138. Min Range: -0.1138

Max Act: 0.1052. Min Act: -0.0004

Data Index: 775970 (C4 (Web Text))

Max Activating Token Index: 57

Text #6

Max Range: 0.1138. Min Range: -0.1138

Max Act: 0.1085. Min Act: -0.0004

Data Index: 892966 (C4 (Web Text))

Max Activating Token Index: 953

Text #7

Max Range: 0.1138. Min Range: -0.1138

Max Act: 0.1039. Min Act: -0.0004

Data Index: 1187273 (C4 (Web Text))

Max Activating Token Index: 283

Text #8

Max Range: 0.1138. Min Range: -0.1138

Max Act: 0.0792. Min Act: -0.0004

Data Index: 519043 (C4 (Web Text))

Max Activating Token Index: 867

Text #9

Max Range: 0.1138. Min Range: -0.1138

Max Act: 0.0822. Min Act: -0.0004

Data Index: 129942 (C4 (Web Text))

Max Activating Token Index: 628

Text #10

Max Range: 0.1138. Min Range: -0.1138

Max Act: 0.1090. Min Act: -0.0004

Data Index: 596528 (C4 (Web Text))

Max Activating Token Index: 65

Text #11

Max Range: 0.1138. Min Range: -0.1138

Max Act: 0.0962. Min Act: -0.0004

Data Index: 873446 (C4 (Web Text))

Max Activating Token Index: 139

Text #12

Max Range: 0.1138. Min Range: -0.1138

Max Act: 0.0987. Min Act: -0.0004

Data Index: 237583 (C4 (Web Text))

Max Activating Token Index: 931

Text #13

Max Range: 0.1138. Min Range: -0.1138

Max Act: 0.0880. Min Act: -0.0004

Data Index: 1347804 (C4 (Web Text))

Max Activating Token Index: 667

Text #14

Max Range: 0.1138. Min Range: -0.1138

Max Act: 0.0914. Min Act: -0.0004

Data Index: 466600 (C4 (Web Text))

Max Activating Token Index: 226

Text #15

Max Range: 0.1138. Min Range: -0.1138

Max Act: 0.0943. Min Act: -0.0004

Data Index: 695770 (C4 (Web Text))

Max Activating Token Index: 732

Text #16

Max Range: 0.1138. Min Range: -0.1138

Max Act: 0.0931. Min Act: -0.0004

Data Index: 310473 (C4 (Web Text))

Max Activating Token Index: 282

Text #17

Max Range: 0.1138. Min Range: -0.1138

Max Act: 0.0623. Min Act: -0.0004

Data Index: 386158 (C4 (Web Text))

Max Activating Token Index: 828

Text #18

Max Range: 0.1138. Min Range: -0.1138

Max Act: 0.1031. Min Act: -0.0004

Data Index: 162168 (C4 (Web Text))

Max Activating Token Index: 885

Text #19

Max Range: 0.1138. Min Range: -0.1138

Max Act: 0.0854. Min Act: -0.0004

Data Index: 459448 (C4 (Web Text))

Max Activating Token Index: 765