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

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

Neuron 1992 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1076. Min Range: -0.1076

Max Act: 0.1076. Min Act: -0.0002

Data Index: 91782 (C4 (Web Text))

Max Activating Token Index: 844

Text #1

Max Range: 0.1076. Min Range: -0.1076

Max Act: 0.1070. Min Act: -0.0003

Data Index: 520751 (C4 (Web Text))

Max Activating Token Index: 38

Text #2

Max Range: 0.1076. Min Range: -0.1076

Max Act: 0.1049. Min Act: -0.0002

Data Index: 1262090 (C4 (Web Text))

Max Activating Token Index: 727

Text #3

Max Range: 0.1076. Min Range: -0.1076

Max Act: 0.0972. Min Act: -0.0003

Data Index: 146538 (C4 (Web Text))

Max Activating Token Index: 338

Text #4

Max Range: 0.1076. Min Range: -0.1076

Max Act: 0.0952. Min Act: -0.0003

Data Index: 595714 (C4 (Web Text))

Max Activating Token Index: 429

Text #5

Max Range: 0.1076. Min Range: -0.1076

Max Act: 0.0892. Min Act: -0.0003

Data Index: 427532 (C4 (Web Text))

Max Activating Token Index: 853

Text #6

Max Range: 0.1076. Min Range: -0.1076

Max Act: 0.0868. Min Act: -0.0002

Data Index: 1255186 (C4 (Web Text))

Max Activating Token Index: 315

Text #7

Max Range: 0.1076. Min Range: -0.1076

Max Act: 0.0858. Min Act: -0.0003

Data Index: 62198 (C4 (Web Text))

Max Activating Token Index: 579

Text #8

Max Range: 0.1076. Min Range: -0.1076

Max Act: 0.0899. Min Act: -0.0003

Data Index: 101074 (C4 (Web Text))

Max Activating Token Index: 796

Text #9

Max Range: 0.1076. Min Range: -0.1076

Max Act: 0.0866. Min Act: -0.0003

Data Index: 12400 (C4 (Web Text))

Max Activating Token Index: 680

Text #10

Max Range: 0.1076. Min Range: -0.1076

Max Act: 0.0812. Min Act: -0.0002

Data Index: 83052 (C4 (Web Text))

Max Activating Token Index: 599

Text #11

Max Range: 0.1076. Min Range: -0.1076

Max Act: 0.0846. Min Act: -0.0003

Data Index: 665162 (C4 (Web Text))

Max Activating Token Index: 885

Text #12

Max Range: 0.1076. Min Range: -0.1076

Max Act: 0.0813. Min Act: -0.0002

Data Index: 340243 (C4 (Web Text))

Max Activating Token Index: 904

Text #13

Max Range: 0.1076. Min Range: -0.1076

Max Act: 0.0804. Min Act: -0.0003

Data Index: 96957 (C4 (Web Text))

Max Activating Token Index: 887

Text #14

Max Range: 0.1076. Min Range: -0.1076

Max Act: 0.0804. Min Act: -0.0002

Data Index: 663546 (C4 (Web Text))

Max Activating Token Index: 505

Text #15

Max Range: 0.1076. Min Range: -0.1076

Max Act: 0.0775. Min Act: -0.0002

Data Index: 37177 (C4 (Web Text))

Max Activating Token Index: 301

Text #16

Max Range: 0.1076. Min Range: -0.1076

Max Act: 0.0801. Min Act: -0.0002

Data Index: 398166 (C4 (Web Text))

Max Activating Token Index: 462

Text #17

Max Range: 0.1076. Min Range: -0.1076

Max Act: 0.0803. Min Act: -0.0002

Data Index: 1044524 (C4 (Web Text))

Max Activating Token Index: 734

Text #18

Max Range: 0.1076. Min Range: -0.1076

Max Act: 0.0793. Min Act: -0.0002

Data Index: 818638 (C4 (Web Text))

Max Activating Token Index: 889

Text #19

Max Range: 0.1076. Min Range: -0.1076

Max Act: 0.0793. Min Act: -0.0003

Data Index: 810751 (C4 (Web Text))

Max Activating Token Index: 601