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

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

Neuron 414 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0998. Min Range: -0.0998

Max Act: 0.0998. Min Act: -0.0002

Data Index: 441947 (C4 (Web Text))

Max Activating Token Index: 769

Text #1

Max Range: 0.0998. Min Range: -0.0998

Max Act: 0.0852. Min Act: -0.0002

Data Index: 553331 (C4 (Web Text))

Max Activating Token Index: 42

Text #2

Max Range: 0.0998. Min Range: -0.0998

Max Act: 0.0877. Min Act: -0.0002

Data Index: 880078 (C4 (Web Text))

Max Activating Token Index: 795

Text #3

Max Range: 0.0998. Min Range: -0.0998

Max Act: 0.0750. Min Act: -0.0002

Data Index: 510934 (C4 (Web Text))

Max Activating Token Index: 765

Text #4

Max Range: 0.0998. Min Range: -0.0998

Max Act: 0.0829. Min Act: -0.0002

Data Index: 469695 (C4 (Web Text))

Max Activating Token Index: 18

Text #5

Max Range: 0.0998. Min Range: -0.0998

Max Act: 0.0894. Min Act: -0.0002

Data Index: 256767 (C4 (Web Text))

Max Activating Token Index: 565

Text #6

Max Range: 0.0998. Min Range: -0.0998

Max Act: 0.0763. Min Act: -0.0002

Data Index: 1233863 (C4 (Web Text))

Max Activating Token Index: 177

Text #7

Max Range: 0.0998. Min Range: -0.0998

Max Act: 0.0843. Min Act: -0.0002

Data Index: 305322 (C4 (Web Text))

Max Activating Token Index: 504

Text #8

Max Range: 0.0998. Min Range: -0.0998

Max Act: 0.0906. Min Act: -0.0002

Data Index: 30877 (C4 (Web Text))

Max Activating Token Index: 38

Text #9

Max Range: 0.0998. Min Range: -0.0998

Max Act: 0.0803. Min Act: -0.0002

Data Index: 592092 (C4 (Web Text))

Max Activating Token Index: 40

Text #10

Max Range: 0.0998. Min Range: -0.0998

Max Act: 0.0744. Min Act: -0.0002

Data Index: 771879 (C4 (Web Text))

Max Activating Token Index: 72

Text #11

Max Range: 0.0998. Min Range: -0.0998

Max Act: 0.0802. Min Act: -0.0002

Data Index: 914547 (C4 (Web Text))

Max Activating Token Index: 572

Text #12

Max Range: 0.0998. Min Range: -0.0998

Max Act: 0.0730. Min Act: -0.0002

Data Index: 1023880 (C4 (Web Text))

Max Activating Token Index: 912

Text #13

Max Range: 0.0998. Min Range: -0.0998

Max Act: 0.0751. Min Act: -0.0002

Data Index: 1137487 (C4 (Web Text))

Max Activating Token Index: 633

Text #14

Max Range: 0.0998. Min Range: -0.0998

Max Act: 0.0849. Min Act: -0.0002

Data Index: 928295 (C4 (Web Text))

Max Activating Token Index: 743

Text #15

Max Range: 0.0998. Min Range: -0.0998

Max Act: 0.0777. Min Act: -0.0002

Data Index: 178007 (C4 (Web Text))

Max Activating Token Index: 300

Text #16

Max Range: 0.0998. Min Range: -0.0998

Max Act: 0.0813. Min Act: -0.0002

Data Index: 131884 (C4 (Web Text))

Max Activating Token Index: 546

Text #17

Max Range: 0.0998. Min Range: -0.0998

Max Act: 0.0924. Min Act: -0.0002

Data Index: 304600 (C4 (Web Text))

Max Activating Token Index: 200

Text #18

Max Range: 0.0998. Min Range: -0.0998

Max Act: 0.0811. Min Act: -0.0002

Data Index: 91209 (C4 (Web Text))

Max Activating Token Index: 34

Text #19

Max Range: 0.0998. Min Range: -0.0998

Max Act: 0.0816. Min Act: -0.0002

Data Index: 404076 (C4 (Web Text))

Max Activating Token Index: 298