Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 800 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.1047. Min Range: -0.1047

Max Act: 0.1044. Min Act: -0.0003

Data Index: 1086995 (C4 (Web Text))

Max Activating Token Index: 730

Text #1

Max Range: 0.1047. Min Range: -0.1047

Max Act: 0.1047. Min Act: -0.0003

Data Index: 303667 (C4 (Web Text))

Max Activating Token Index: 789

Text #2

Max Range: 0.1047. Min Range: -0.1047

Max Act: 0.1047. Min Act: -0.0004

Data Index: 416868 (C4 (Web Text))

Max Activating Token Index: 359

Text #3

Max Range: 0.1047. Min Range: -0.1047

Max Act: 0.1002. Min Act: -0.0003

Data Index: 1197858 (C4 (Web Text))

Max Activating Token Index: 993

Text #4

Max Range: 0.1047. Min Range: -0.1047

Max Act: 0.0979. Min Act: -0.0003

Data Index: 1217463 (C4 (Web Text))

Max Activating Token Index: 736

Text #5

Max Range: 0.1047. Min Range: -0.1047

Max Act: 0.0974. Min Act: -0.0003

Data Index: 934603 (C4 (Web Text))

Max Activating Token Index: 664

Text #6

Max Range: 0.1047. Min Range: -0.1047

Max Act: 0.0954. Min Act: -0.0003

Data Index: 901375 (C4 (Web Text))

Max Activating Token Index: 662

Text #7

Max Range: 0.1047. Min Range: -0.1047

Max Act: 0.0974. Min Act: -0.0003

Data Index: 667032 (C4 (Web Text))

Max Activating Token Index: 933

Text #8

Max Range: 0.1047. Min Range: -0.1047

Max Act: 0.0931. Min Act: -0.0003

Data Index: 365352 (C4 (Web Text))

Max Activating Token Index: 939

Text #9

Max Range: 0.1047. Min Range: -0.1047

Max Act: 0.0906. Min Act: -0.0003

Data Index: 464671 (C4 (Web Text))

Max Activating Token Index: 737

Text #10

Max Range: 0.1047. Min Range: -0.1047

Max Act: 0.0969. Min Act: -0.0003

Data Index: 1077218 (C4 (Web Text))

Max Activating Token Index: 909

Text #11

Max Range: 0.1047. Min Range: -0.1047

Max Act: 0.0962. Min Act: -0.0003

Data Index: 599625 (C4 (Web Text))

Max Activating Token Index: 876

Text #12

Max Range: 0.1047. Min Range: -0.1047

Max Act: 0.0894. Min Act: -0.0003

Data Index: 1134320 (C4 (Web Text))

Max Activating Token Index: 799

Text #13

Max Range: 0.1047. Min Range: -0.1047

Max Act: 0.0924. Min Act: -0.0002

Data Index: 92302 (C4 (Web Text))

Max Activating Token Index: 680

Text #14

Max Range: 0.1047. Min Range: -0.1047

Max Act: 0.0987. Min Act: -0.0004

Data Index: 1188843 (C4 (Web Text))

Max Activating Token Index: 703

Text #15

Max Range: 0.1047. Min Range: -0.1047

Max Act: 0.0880. Min Act: -0.0004

Data Index: 1023623 (C4 (Web Text))

Max Activating Token Index: 171

Text #16

Max Range: 0.1047. Min Range: -0.1047

Max Act: 0.0885. Min Act: -0.0003

Data Index: 764439 (C4 (Web Text))

Max Activating Token Index: 696

Text #17

Max Range: 0.1047. Min Range: -0.1047

Max Act: 0.0880. Min Act: -0.0004

Data Index: 593425 (C4 (Web Text))

Max Activating Token Index: 895

Text #18

Max Range: 0.1047. Min Range: -0.1047

Max Act: 0.0919. Min Act: -0.0003

Data Index: 107990 (C4 (Web Text))

Max Activating Token Index: 32

Text #19

Max Range: 0.1047. Min Range: -0.1047

Max Act: 0.0853. Min Act: -0.0003

Data Index: 200713 (C4 (Web Text))

Max Activating Token Index: 210