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

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

Neuron 95 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: 0.1046. Min Range: -0.1046

Max Act: 0.1046. Min Act: -0.0001

Data Index: 712795 (C4 (Web Text))

Max Activating Token Index: 948

Text #1

Max Range: 0.1046. Min Range: -0.1046

Max Act: 0.1007. Min Act: -0.0002

Data Index: 1609573 (Python Code)

Max Activating Token Index: 475

Text #2

Max Range: 0.1046. Min Range: -0.1046

Max Act: 0.0970. Min Act: -0.0002

Data Index: 701526 (C4 (Web Text))

Max Activating Token Index: 229

Text #3

Max Range: 0.1046. Min Range: -0.1046

Max Act: 0.0921. Min Act: -0.0001

Data Index: 1510541 (Python Code)

Max Activating Token Index: 1011

Text #4

Max Range: 0.1046. Min Range: -0.1046

Max Act: 0.0895. Min Act: -0.0002

Data Index: 1430525 (Python Code)

Max Activating Token Index: 912

Text #5

Max Range: 0.1046. Min Range: -0.1046

Max Act: 0.0960. Min Act: 0.0000

Data Index: 1468657 (Python Code)

Max Activating Token Index: 83

Text #6

Max Range: 0.1046. Min Range: -0.1046

Max Act: 0.0905. Min Act: -0.0002

Data Index: 1090095 (C4 (Web Text))

Max Activating Token Index: 41

Text #7

Max Range: 0.1046. Min Range: -0.1046

Max Act: 0.0856. Min Act: -0.0002

Data Index: 856795 (C4 (Web Text))

Max Activating Token Index: 172

Text #8

Max Range: 0.1046. Min Range: -0.1046

Max Act: 0.0887. Min Act: -0.0001

Data Index: 1572612 (Python Code)

Max Activating Token Index: 738

Text #9

Max Range: 0.1046. Min Range: -0.1046

Max Act: 0.0858. Min Act: -0.0002

Data Index: 825951 (C4 (Web Text))

Max Activating Token Index: 808

Text #10

Max Range: 0.1046. Min Range: -0.1046

Max Act: 0.0870. Min Act: -0.0002

Data Index: 31906 (C4 (Web Text))

Max Activating Token Index: 60

Text #11

Max Range: 0.1046. Min Range: -0.1046

Max Act: 0.0879. Min Act: -0.0000

Data Index: 1474524 (Python Code)

Max Activating Token Index: 546

Text #12

Max Range: 0.1046. Min Range: -0.1046

Max Act: 0.0851. Min Act: 0.0000

Data Index: 69197 (C4 (Web Text))

Max Activating Token Index: 13

Text #13

Max Range: 0.1046. Min Range: -0.1046

Max Act: 0.0840. Min Act: -0.0002

Data Index: 874847 (C4 (Web Text))

Max Activating Token Index: 594

Text #14

Max Range: 0.1046. Min Range: -0.1046

Max Act: 0.0843. Min Act: -0.0002

Data Index: 356689 (C4 (Web Text))

Max Activating Token Index: 868

Text #15

Max Range: 0.1046. Min Range: -0.1046

Max Act: 0.0867. Min Act: -0.0002

Data Index: 430735 (C4 (Web Text))

Max Activating Token Index: 117

Text #16

Max Range: 0.1046. Min Range: -0.1046

Max Act: 0.0837. Min Act: -0.0001

Data Index: 1440899 (Python Code)

Max Activating Token Index: 881

Text #17

Max Range: 0.1046. Min Range: -0.1046

Max Act: 0.0792. Min Act: -0.0002

Data Index: 61575 (C4 (Web Text))

Max Activating Token Index: 95

Text #18

Max Range: 0.1046. Min Range: -0.1046

Max Act: 0.0820. Min Act: 0.0000

Data Index: 590951 (C4 (Web Text))

Max Activating Token Index: 111

Text #19

Max Range: 0.1046. Min Range: -0.1046

Max Act: 0.0806. Min Act: -0.0002

Data Index: 972796 (C4 (Web Text))

Max Activating Token Index: 918