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

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

Neuron 2100 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: 0.0829. Min Range: -0.0829

Max Act: 0.0798. Min Act: -0.0002

Data Index: 907393 (C4 (Web Text))

Max Activating Token Index: 729

Text #1

Max Range: 0.0829. Min Range: -0.0829

Max Act: 0.0810. Min Act: -0.0002

Data Index: 94990 (C4 (Web Text))

Max Activating Token Index: 903

Text #2

Max Range: 0.0829. Min Range: -0.0829

Max Act: 0.0793. Min Act: -0.0002

Data Index: 791104 (C4 (Web Text))

Max Activating Token Index: 56

Text #3

Max Range: 0.0829. Min Range: -0.0829

Max Act: 0.0788. Min Act: -0.0002

Data Index: 137857 (C4 (Web Text))

Max Activating Token Index: 121

Text #4

Max Range: 0.0829. Min Range: -0.0829

Max Act: 0.0801. Min Act: -0.0002

Data Index: 896341 (C4 (Web Text))

Max Activating Token Index: 752

Text #5

Max Range: 0.0829. Min Range: -0.0829

Max Act: 0.0829. Min Act: -0.0002

Data Index: 256010 (C4 (Web Text))

Max Activating Token Index: 983

Text #6

Max Range: 0.0829. Min Range: -0.0829

Max Act: 0.0813. Min Act: -0.0002

Data Index: 178835 (C4 (Web Text))

Max Activating Token Index: 54

Text #7

Max Range: 0.0829. Min Range: -0.0829

Max Act: 0.0727. Min Act: -0.0002

Data Index: 1104401 (C4 (Web Text))

Max Activating Token Index: 79

Text #8

Max Range: 0.0829. Min Range: -0.0829

Max Act: 0.0783. Min Act: -0.0002

Data Index: 1148052 (C4 (Web Text))

Max Activating Token Index: 82

Text #9

Max Range: 0.0829. Min Range: -0.0829

Max Act: 0.0716. Min Act: -0.0002

Data Index: 71986 (C4 (Web Text))

Max Activating Token Index: 722

Text #10

Max Range: 0.0829. Min Range: -0.0829

Max Act: 0.0660. Min Act: -0.0002

Data Index: 598412 (C4 (Web Text))

Max Activating Token Index: 110

Text #11

Max Range: 0.0829. Min Range: -0.0829

Max Act: 0.0762. Min Act: -0.0002

Data Index: 514192 (C4 (Web Text))

Max Activating Token Index: 450

Text #12

Max Range: 0.0829. Min Range: -0.0829

Max Act: 0.0734. Min Act: -0.0002

Data Index: 81681 (C4 (Web Text))

Max Activating Token Index: 455

Text #13

Max Range: 0.0829. Min Range: -0.0829

Max Act: 0.0705. Min Act: -0.0002

Data Index: 585145 (C4 (Web Text))

Max Activating Token Index: 232

Text #14

Max Range: 0.0829. Min Range: -0.0829

Max Act: 0.0703. Min Act: -0.0002

Data Index: 838404 (C4 (Web Text))

Max Activating Token Index: 976

Text #15

Max Range: 0.0829. Min Range: -0.0829

Max Act: 0.0714. Min Act: -0.0002

Data Index: 157725 (C4 (Web Text))

Max Activating Token Index: 766

Text #16

Max Range: 0.0829. Min Range: -0.0829

Max Act: 0.0724. Min Act: -0.0002

Data Index: 986157 (C4 (Web Text))

Max Activating Token Index: 958

Text #17

Max Range: 0.0829. Min Range: -0.0829

Max Act: 0.0671. Min Act: -0.0002

Data Index: 771348 (C4 (Web Text))

Max Activating Token Index: 735

Text #18

Max Range: 0.0829. Min Range: -0.0829

Max Act: 0.0711. Min Act: -0.0002

Data Index: 720978 (C4 (Web Text))

Max Activating Token Index: 194

Text #19

Max Range: 0.0829. Min Range: -0.0829

Max Act: 0.0679. Min Act: -0.0002

Data Index: 845637 (C4 (Web Text))

Max Activating Token Index: 115