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

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

Neuron 2200 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: 0.1072. Min Range: -0.1072

Max Act: 0.1072. Min Act: -0.0002

Data Index: 866912 (C4 (Web Text))

Max Activating Token Index: 209

Text #1

Max Range: 0.1072. Min Range: -0.1072

Max Act: 0.1046. Min Act: -0.0002

Data Index: 731933 (C4 (Web Text))

Max Activating Token Index: 665

Text #2

Max Range: 0.1072. Min Range: -0.1072

Max Act: 0.1027. Min Act: -0.0002

Data Index: 428118 (C4 (Web Text))

Max Activating Token Index: 500

Text #3

Max Range: 0.1072. Min Range: -0.1072

Max Act: 0.1007. Min Act: -0.0002

Data Index: 1090584 (C4 (Web Text))

Max Activating Token Index: 419

Text #4

Max Range: 0.1072. Min Range: -0.1072

Max Act: 0.1036. Min Act: -0.0002

Data Index: 637388 (C4 (Web Text))

Max Activating Token Index: 45

Text #5

Max Range: 0.1072. Min Range: -0.1072

Max Act: 0.1034. Min Act: -0.0002

Data Index: 1243004 (C4 (Web Text))

Max Activating Token Index: 28

Text #6

Max Range: 0.1072. Min Range: -0.1072

Max Act: 0.0953. Min Act: -0.0002

Data Index: 531674 (C4 (Web Text))

Max Activating Token Index: 226

Text #7

Max Range: 0.1072. Min Range: -0.1072

Max Act: 0.1015. Min Act: -0.0002

Data Index: 805581 (C4 (Web Text))

Max Activating Token Index: 456

Text #8

Max Range: 0.1072. Min Range: -0.1072

Max Act: 0.0962. Min Act: -0.0002

Data Index: 1137010 (C4 (Web Text))

Max Activating Token Index: 753

Text #9

Max Range: 0.1072. Min Range: -0.1072

Max Act: 0.0890. Min Act: -0.0002

Data Index: 286604 (C4 (Web Text))

Max Activating Token Index: 56

Text #10

Max Range: 0.1072. Min Range: -0.1072

Max Act: 0.0995. Min Act: -0.0002

Data Index: 219123 (C4 (Web Text))

Max Activating Token Index: 39

Text #11

Max Range: 0.1072. Min Range: -0.1072

Max Act: 0.0912. Min Act: -0.0002

Data Index: 1072873 (C4 (Web Text))

Max Activating Token Index: 540

Text #12

Max Range: 0.1072. Min Range: -0.1072

Max Act: 0.0943. Min Act: -0.0002

Data Index: 235422 (C4 (Web Text))

Max Activating Token Index: 28

Text #13

Max Range: 0.1072. Min Range: -0.1072

Max Act: 0.0983. Min Act: -0.0002

Data Index: 468045 (C4 (Web Text))

Max Activating Token Index: 157

Text #14

Max Range: 0.1072. Min Range: -0.1072

Max Act: 0.0920. Min Act: -0.0002

Data Index: 488600 (C4 (Web Text))

Max Activating Token Index: 12

Text #15

Max Range: 0.1072. Min Range: -0.1072

Max Act: 0.0966. Min Act: -0.0002

Data Index: 777786 (C4 (Web Text))

Max Activating Token Index: 87

Text #16

Max Range: 0.1072. Min Range: -0.1072

Max Act: 0.0873. Min Act: -0.0002

Data Index: 1017184 (C4 (Web Text))

Max Activating Token Index: 227

Text #17

Max Range: 0.1072. Min Range: -0.1072

Max Act: 0.0866. Min Act: -0.0002

Data Index: 1254385 (C4 (Web Text))

Max Activating Token Index: 36

Text #18

Max Range: 0.1072. Min Range: -0.1072

Max Act: 0.0872. Min Act: -0.0002

Data Index: 937718 (C4 (Web Text))

Max Activating Token Index: 24

Text #19

Max Range: 0.1072. Min Range: -0.1072

Max Act: 0.0861. Min Act: -0.0002

Data Index: 288681 (C4 (Web Text))

Max Activating Token Index: 209