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

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

Neuron 3375 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1114. Min Range: -0.1114

Max Act: 0.1114. Min Act: -0.0002

Data Index: 1069635 (C4 (Web Text))

Max Activating Token Index: 136

Text #1

Max Range: 0.1114. Min Range: -0.1114

Max Act: 0.1021. Min Act: -0.0002

Data Index: 262630 (C4 (Web Text))

Max Activating Token Index: 30

Text #2

Max Range: 0.1114. Min Range: -0.1114

Max Act: 0.0990. Min Act: -0.0002

Data Index: 854496 (C4 (Web Text))

Max Activating Token Index: 404

Text #3

Max Range: 0.1114. Min Range: -0.1114

Max Act: 0.0980. Min Act: -0.0002

Data Index: 1264448 (C4 (Web Text))

Max Activating Token Index: 71

Text #4

Max Range: 0.1114. Min Range: -0.1114

Max Act: 0.0904. Min Act: -0.0002

Data Index: 862916 (C4 (Web Text))

Max Activating Token Index: 90

Text #5

Max Range: 0.1114. Min Range: -0.1114

Max Act: 0.0889. Min Act: -0.0002

Data Index: 245305 (C4 (Web Text))

Max Activating Token Index: 940

Text #6

Max Range: 0.1114. Min Range: -0.1114

Max Act: 0.0877. Min Act: -0.0002

Data Index: 1305968 (C4 (Web Text))

Max Activating Token Index: 496

Text #7

Max Range: 0.1114. Min Range: -0.1114

Max Act: 0.0860. Min Act: -0.0002

Data Index: 771002 (C4 (Web Text))

Max Activating Token Index: 371

Text #8

Max Range: 0.1114. Min Range: -0.1114

Max Act: 0.0859. Min Act: -0.0002

Data Index: 522222 (C4 (Web Text))

Max Activating Token Index: 184

Text #9

Max Range: 0.1114. Min Range: -0.1114

Max Act: 0.0854. Min Act: -0.0002

Data Index: 454437 (C4 (Web Text))

Max Activating Token Index: 20

Text #10

Max Range: 0.1114. Min Range: -0.1114

Max Act: 0.0851. Min Act: -0.0002

Data Index: 205830 (C4 (Web Text))

Max Activating Token Index: 778

Text #11

Max Range: 0.1114. Min Range: -0.1114

Max Act: 0.0836. Min Act: -0.0002

Data Index: 1019763 (C4 (Web Text))

Max Activating Token Index: 491

Text #12

Max Range: 0.1114. Min Range: -0.1114

Max Act: 0.0829. Min Act: -0.0002

Data Index: 926228 (C4 (Web Text))

Max Activating Token Index: 489

Text #13

Max Range: 0.1114. Min Range: -0.1114

Max Act: 0.0827. Min Act: -0.0002

Data Index: 129351 (C4 (Web Text))

Max Activating Token Index: 27

Text #14

Max Range: 0.1114. Min Range: -0.1114

Max Act: 0.0817. Min Act: -0.0002

Data Index: 116779 (C4 (Web Text))

Max Activating Token Index: 933

Text #15

Max Range: 0.1114. Min Range: -0.1114

Max Act: 0.0815. Min Act: -0.0002

Data Index: 208654 (C4 (Web Text))

Max Activating Token Index: 344

Text #16

Max Range: 0.1114. Min Range: -0.1114

Max Act: 0.0791. Min Act: -0.0002

Data Index: 468264 (C4 (Web Text))

Max Activating Token Index: 927

Text #17

Max Range: 0.1114. Min Range: -0.1114

Max Act: 0.0779. Min Act: -0.0002

Data Index: 1244516 (C4 (Web Text))

Max Activating Token Index: 53

Text #18

Max Range: 0.1114. Min Range: -0.1114

Max Act: 0.0772. Min Act: -0.0002

Data Index: 1200433 (C4 (Web Text))

Max Activating Token Index: 359

Text #19

Max Range: 0.1114. Min Range: -0.1114

Max Act: 0.0768. Min Act: -0.0002

Data Index: 1083063 (C4 (Web Text))

Max Activating Token Index: 59