Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1836 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.1027. Min Range: -0.1027

Max Act: 0.1027. Min Act: -0.0003

Data Index: 107325 (C4 (Web Text))

Max Activating Token Index: 456

Text #1

Max Range: 0.1027. Min Range: -0.1027

Max Act: 0.1020. Min Act: -0.0004

Data Index: 1345392 (C4 (Web Text))

Max Activating Token Index: 912

Text #2

Max Range: 0.1027. Min Range: -0.1027

Max Act: 0.1001. Min Act: -0.0004

Data Index: 1272170 (C4 (Web Text))

Max Activating Token Index: 85

Text #3

Max Range: 0.1027. Min Range: -0.1027

Max Act: 0.1004. Min Act: -0.0003

Data Index: 562304 (C4 (Web Text))

Max Activating Token Index: 129

Text #4

Max Range: 0.1027. Min Range: -0.1027

Max Act: 0.0980. Min Act: -0.0003

Data Index: 795280 (C4 (Web Text))

Max Activating Token Index: 20

Text #5

Max Range: 0.1027. Min Range: -0.1027

Max Act: 0.0915. Min Act: -0.0003

Data Index: 1300166 (C4 (Web Text))

Max Activating Token Index: 592

Text #6

Max Range: 0.1027. Min Range: -0.1027

Max Act: 0.0907. Min Act: -0.0003

Data Index: 353246 (C4 (Web Text))

Max Activating Token Index: 809

Text #7

Max Range: 0.1027. Min Range: -0.1027

Max Act: 0.0889. Min Act: -0.0003

Data Index: 93073 (C4 (Web Text))

Max Activating Token Index: 607

Text #8

Max Range: 0.1027. Min Range: -0.1027

Max Act: 0.0849. Min Act: -0.0003

Data Index: 837483 (C4 (Web Text))

Max Activating Token Index: 701

Text #9

Max Range: 0.1027. Min Range: -0.1027

Max Act: 0.0886. Min Act: -0.0002

Data Index: 583563 (C4 (Web Text))

Max Activating Token Index: 302

Text #10

Max Range: 0.1027. Min Range: -0.1027

Max Act: 0.0876. Min Act: -0.0003

Data Index: 520077 (C4 (Web Text))

Max Activating Token Index: 24

Text #11

Max Range: 0.1027. Min Range: -0.1027

Max Act: 0.0864. Min Act: -0.0002

Data Index: 125526 (C4 (Web Text))

Max Activating Token Index: 383

Text #12

Max Range: 0.1027. Min Range: -0.1027

Max Act: 0.0847. Min Act: -0.0004

Data Index: 1201378 (C4 (Web Text))

Max Activating Token Index: 454

Text #13

Max Range: 0.1027. Min Range: -0.1027

Max Act: 0.0862. Min Act: -0.0003

Data Index: 78041 (C4 (Web Text))

Max Activating Token Index: 557

Text #14

Max Range: 0.1027. Min Range: -0.1027

Max Act: 0.0873. Min Act: -0.0003

Data Index: 213965 (C4 (Web Text))

Max Activating Token Index: 381

Text #15

Max Range: 0.1027. Min Range: -0.1027

Max Act: 0.0836. Min Act: -0.0003

Data Index: 322579 (C4 (Web Text))

Max Activating Token Index: 175

Text #16

Max Range: 0.1027. Min Range: -0.1027

Max Act: 0.0870. Min Act: -0.0002

Data Index: 1014851 (C4 (Web Text))

Max Activating Token Index: 127

Text #17

Max Range: 0.1027. Min Range: -0.1027

Max Act: 0.0847. Min Act: -0.0004

Data Index: 125717 (C4 (Web Text))

Max Activating Token Index: 714

Text #18

Max Range: 0.1027. Min Range: -0.1027

Max Act: 0.0839. Min Act: -0.0003

Data Index: 906912 (C4 (Web Text))

Max Activating Token Index: 592

Text #19

Max Range: 0.1027. Min Range: -0.1027

Max Act: 0.0900. Min Act: -0.0003

Data Index: 594780 (C4 (Web Text))

Max Activating Token Index: 821