Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 769 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1059. Min Range: -0.1059

Max Act: 0.1059. Min Act: -0.0002

Data Index: 206681 (C4 (Web Text))

Max Activating Token Index: 156

Text #1

Max Range: 0.1059. Min Range: -0.1059

Max Act: 0.0953. Min Act: -0.0002

Data Index: 627371 (C4 (Web Text))

Max Activating Token Index: 70

Text #2

Max Range: 0.1059. Min Range: -0.1059

Max Act: 0.0911. Min Act: -0.0002

Data Index: 874973 (C4 (Web Text))

Max Activating Token Index: 750

Text #3

Max Range: 0.1059. Min Range: -0.1059

Max Act: 0.0899. Min Act: -0.0001

Data Index: 281448 (C4 (Web Text))

Max Activating Token Index: 78

Text #4

Max Range: 0.1059. Min Range: -0.1059

Max Act: 0.0916. Min Act: -0.0002

Data Index: 949696 (C4 (Web Text))

Max Activating Token Index: 515

Text #5

Max Range: 0.1059. Min Range: -0.1059

Max Act: 0.0895. Min Act: -0.0001

Data Index: 372097 (C4 (Web Text))

Max Activating Token Index: 171

Text #6

Max Range: 0.1059. Min Range: -0.1059

Max Act: 0.0906. Min Act: -0.0002

Data Index: 538726 (C4 (Web Text))

Max Activating Token Index: 799

Text #7

Max Range: 0.1059. Min Range: -0.1059

Max Act: 0.0875. Min Act: -0.0001

Data Index: 680774 (C4 (Web Text))

Max Activating Token Index: 308

Text #8

Max Range: 0.1059. Min Range: -0.1059

Max Act: 0.0902. Min Act: -0.0001

Data Index: 595938 (C4 (Web Text))

Max Activating Token Index: 194

Text #9

Max Range: 0.1059. Min Range: -0.1059

Max Act: 0.0893. Min Act: -0.0001

Data Index: 340695 (C4 (Web Text))

Max Activating Token Index: 711

Text #10

Max Range: 0.1059. Min Range: -0.1059

Max Act: 0.0842. Min Act: -0.0002

Data Index: 559761 (C4 (Web Text))

Max Activating Token Index: 592

Text #11

Max Range: 0.1059. Min Range: -0.1059

Max Act: 0.0837. Min Act: -0.0002

Data Index: 635836 (C4 (Web Text))

Max Activating Token Index: 527

Text #12

Max Range: 0.1059. Min Range: -0.1059

Max Act: 0.0854. Min Act: -0.0002

Data Index: 124458 (C4 (Web Text))

Max Activating Token Index: 29

Text #13

Max Range: 0.1059. Min Range: -0.1059

Max Act: 0.0856. Min Act: -0.0002

Data Index: 1112427 (C4 (Web Text))

Max Activating Token Index: 122

Text #14

Max Range: 0.1059. Min Range: -0.1059

Max Act: 0.0861. Min Act: -0.0002

Data Index: 1249308 (C4 (Web Text))

Max Activating Token Index: 145

Text #15

Max Range: 0.1059. Min Range: -0.1059

Max Act: 0.0878. Min Act: -0.0002

Data Index: 239931 (C4 (Web Text))

Max Activating Token Index: 686

Text #16

Max Range: 0.1059. Min Range: -0.1059

Max Act: 0.0744. Min Act: -0.0002

Data Index: 6657 (C4 (Web Text))

Max Activating Token Index: 306

Text #17

Max Range: 0.1059. Min Range: -0.1059

Max Act: 0.0834. Min Act: -0.0002

Data Index: 1253581 (C4 (Web Text))

Max Activating Token Index: 888

Text #18

Max Range: 0.1059. Min Range: -0.1059

Max Act: 0.0822. Min Act: -0.0002

Data Index: 669226 (C4 (Web Text))

Max Activating Token Index: 365

Text #19

Max Range: 0.1059. Min Range: -0.1059

Max Act: 0.0817. Min Act: -0.0002

Data Index: 1045564 (C4 (Web Text))

Max Activating Token Index: 586