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

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

Neuron 509 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: 0.0962. Min Range: -0.0962

Max Act: 0.0883. Min Act: -0.0002

Data Index: 931180 (C4 (Web Text))

Max Activating Token Index: 842

Text #1

Max Range: 0.0962. Min Range: -0.0962

Max Act: 0.0962. Min Act: -0.0002

Data Index: 617502 (C4 (Web Text))

Max Activating Token Index: 104

Text #2

Max Range: 0.0962. Min Range: -0.0962

Max Act: 0.0895. Min Act: -0.0002

Data Index: 26214 (C4 (Web Text))

Max Activating Token Index: 134

Text #3

Max Range: 0.0962. Min Range: -0.0962

Max Act: 0.0900. Min Act: -0.0002

Data Index: 555228 (C4 (Web Text))

Max Activating Token Index: 70

Text #4

Max Range: 0.0962. Min Range: -0.0962

Max Act: 0.0918. Min Act: -0.0002

Data Index: 1212007 (C4 (Web Text))

Max Activating Token Index: 390

Text #5

Max Range: 0.0962. Min Range: -0.0962

Max Act: 0.0920. Min Act: -0.0002

Data Index: 997104 (C4 (Web Text))

Max Activating Token Index: 97

Text #6

Max Range: 0.0962. Min Range: -0.0962

Max Act: 0.0872. Min Act: -0.0002

Data Index: 156872 (C4 (Web Text))

Max Activating Token Index: 902

Text #7

Max Range: 0.0962. Min Range: -0.0962

Max Act: 0.0807. Min Act: -0.0002

Data Index: 77230 (C4 (Web Text))

Max Activating Token Index: 629

Text #8

Max Range: 0.0962. Min Range: -0.0962

Max Act: 0.0807. Min Act: -0.0002

Data Index: 75771 (C4 (Web Text))

Max Activating Token Index: 69

Text #9

Max Range: 0.0962. Min Range: -0.0962

Max Act: 0.0837. Min Act: -0.0002

Data Index: 166474 (C4 (Web Text))

Max Activating Token Index: 55

Text #10

Max Range: 0.0962. Min Range: -0.0962

Max Act: 0.0829. Min Act: -0.0002

Data Index: 1269420 (C4 (Web Text))

Max Activating Token Index: 91

Text #11

Max Range: 0.0962. Min Range: -0.0962

Max Act: 0.0824. Min Act: -0.0002

Data Index: 1219259 (C4 (Web Text))

Max Activating Token Index: 90

Text #12

Max Range: 0.0962. Min Range: -0.0962

Max Act: 0.0854. Min Act: -0.0002

Data Index: 877450 (C4 (Web Text))

Max Activating Token Index: 175

Text #13

Max Range: 0.0962. Min Range: -0.0962

Max Act: 0.0815. Min Act: -0.0002

Data Index: 47258 (C4 (Web Text))

Max Activating Token Index: 243

Text #14

Max Range: 0.0962. Min Range: -0.0962

Max Act: 0.0831. Min Act: -0.0002

Data Index: 60002 (C4 (Web Text))

Max Activating Token Index: 981

Text #15

Max Range: 0.0962. Min Range: -0.0962

Max Act: 0.0795. Min Act: -0.0002

Data Index: 246725 (C4 (Web Text))

Max Activating Token Index: 61

Text #16

Max Range: 0.0962. Min Range: -0.0962

Max Act: 0.0757. Min Act: -0.0002

Data Index: 219299 (C4 (Web Text))

Max Activating Token Index: 721

Text #17

Max Range: 0.0962. Min Range: -0.0962

Max Act: 0.0787. Min Act: -0.0002

Data Index: 419649 (C4 (Web Text))

Max Activating Token Index: 659

Text #18

Max Range: 0.0962. Min Range: -0.0962

Max Act: 0.0780. Min Act: -0.0002

Data Index: 700111 (C4 (Web Text))

Max Activating Token Index: 837

Text #19

Max Range: 0.0962. Min Range: -0.0962

Max Act: 0.0796. Min Act: -0.0002

Data Index: 734397 (C4 (Web Text))

Max Activating Token Index: 955