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

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

Neuron 4757 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1092. Min Range: -0.1092

Max Act: 0.1092. Min Act: -0.0002

Data Index: 1330712 (C4 (Web Text))

Max Activating Token Index: 906

Text #1

Max Range: 0.1092. Min Range: -0.1092

Max Act: 0.1057. Min Act: -0.0002

Data Index: 343630 (C4 (Web Text))

Max Activating Token Index: 466

Text #2

Max Range: 0.1092. Min Range: -0.1092

Max Act: 0.1026. Min Act: -0.0002

Data Index: 337221 (C4 (Web Text))

Max Activating Token Index: 110

Text #3

Max Range: 0.1092. Min Range: -0.1092

Max Act: 0.0977. Min Act: -0.0002

Data Index: 627029 (C4 (Web Text))

Max Activating Token Index: 306

Text #4

Max Range: 0.1092. Min Range: -0.1092

Max Act: 0.0947. Min Act: -0.0002

Data Index: 542931 (C4 (Web Text))

Max Activating Token Index: 561

Text #5

Max Range: 0.1092. Min Range: -0.1092

Max Act: 0.1002. Min Act: -0.0002

Data Index: 667787 (C4 (Web Text))

Max Activating Token Index: 80

Text #6

Max Range: 0.1092. Min Range: -0.1092

Max Act: 0.0916. Min Act: -0.0002

Data Index: 490545 (C4 (Web Text))

Max Activating Token Index: 427

Text #7

Max Range: 0.1092. Min Range: -0.1092

Max Act: 0.0888. Min Act: -0.0003

Data Index: 675282 (C4 (Web Text))

Max Activating Token Index: 277

Text #8

Max Range: 0.1092. Min Range: -0.1092

Max Act: 0.0950. Min Act: -0.0002

Data Index: 1267128 (C4 (Web Text))

Max Activating Token Index: 870

Text #9

Max Range: 0.1092. Min Range: -0.1092

Max Act: 0.0928. Min Act: -0.0002

Data Index: 49840 (C4 (Web Text))

Max Activating Token Index: 336

Text #10

Max Range: 0.1092. Min Range: -0.1092

Max Act: 0.1059. Min Act: -0.0002

Data Index: 557082 (C4 (Web Text))

Max Activating Token Index: 780

Text #11

Max Range: 0.1092. Min Range: -0.1092

Max Act: 0.0895. Min Act: -0.0002

Data Index: 334354 (C4 (Web Text))

Max Activating Token Index: 308

Text #12

Max Range: 0.1092. Min Range: -0.1092

Max Act: 0.0889. Min Act: -0.0002

Data Index: 1106746 (C4 (Web Text))

Max Activating Token Index: 561

Text #13

Max Range: 0.1092. Min Range: -0.1092

Max Act: 0.0849. Min Act: -0.0002

Data Index: 1111821 (C4 (Web Text))

Max Activating Token Index: 808

Text #14

Max Range: 0.1092. Min Range: -0.1092

Max Act: 0.0863. Min Act: -0.0002

Data Index: 869726 (C4 (Web Text))

Max Activating Token Index: 933

Text #15

Max Range: 0.1092. Min Range: -0.1092

Max Act: 0.0890. Min Act: -0.0002

Data Index: 246381 (C4 (Web Text))

Max Activating Token Index: 174

Text #16

Max Range: 0.1092. Min Range: -0.1092

Max Act: 0.0893. Min Act: -0.0002

Data Index: 1288492 (C4 (Web Text))

Max Activating Token Index: 851

Text #17

Max Range: 0.1092. Min Range: -0.1092

Max Act: 0.0891. Min Act: -0.0002

Data Index: 656400 (C4 (Web Text))

Max Activating Token Index: 371

Text #18

Max Range: 0.1092. Min Range: -0.1092

Max Act: 0.0943. Min Act: -0.0002

Data Index: 67283 (C4 (Web Text))

Max Activating Token Index: 667

Text #19

Max Range: 0.1092. Min Range: -0.1092

Max Act: 0.0894. Min Act: -0.0002

Data Index: 987985 (C4 (Web Text))

Max Activating Token Index: 733