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

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

Neuron 688 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: 0.1357. Min Range: -0.1357

Max Act: 0.1357. Min Act: -0.0002

Data Index: 270705 (C4 (Web Text))

Max Activating Token Index: 129

Text #1

Max Range: 0.1357. Min Range: -0.1357

Max Act: 0.1145. Min Act: -0.0002

Data Index: 258511 (C4 (Web Text))

Max Activating Token Index: 357

Text #2

Max Range: 0.1357. Min Range: -0.1357

Max Act: 0.1111. Min Act: -0.0002

Data Index: 16994 (C4 (Web Text))

Max Activating Token Index: 321

Text #3

Max Range: 0.1357. Min Range: -0.1357

Max Act: 0.1050. Min Act: -0.0002

Data Index: 1338087 (C4 (Web Text))

Max Activating Token Index: 90

Text #4

Max Range: 0.1357. Min Range: -0.1357

Max Act: 0.0994. Min Act: -0.0002

Data Index: 85906 (C4 (Web Text))

Max Activating Token Index: 187

Text #5

Max Range: 0.1357. Min Range: -0.1357

Max Act: 0.1033. Min Act: -0.0002

Data Index: 1226684 (C4 (Web Text))

Max Activating Token Index: 48

Text #6

Max Range: 0.1357. Min Range: -0.1357

Max Act: 0.0961. Min Act: -0.0002

Data Index: 1067757 (C4 (Web Text))

Max Activating Token Index: 48

Text #7

Max Range: 0.1357. Min Range: -0.1357

Max Act: 0.0976. Min Act: -0.0002

Data Index: 431535 (C4 (Web Text))

Max Activating Token Index: 73

Text #8

Max Range: 0.1357. Min Range: -0.1357

Max Act: 0.0948. Min Act: -0.0002

Data Index: 1119892 (C4 (Web Text))

Max Activating Token Index: 771

Text #9

Max Range: 0.1357. Min Range: -0.1357

Max Act: 0.0970. Min Act: -0.0002

Data Index: 634013 (C4 (Web Text))

Max Activating Token Index: 990

Text #10

Max Range: 0.1357. Min Range: -0.1357

Max Act: 0.0926. Min Act: -0.0002

Data Index: 569600 (C4 (Web Text))

Max Activating Token Index: 45

Text #11

Max Range: 0.1357. Min Range: -0.1357

Max Act: 0.0928. Min Act: -0.0002

Data Index: 440892 (C4 (Web Text))

Max Activating Token Index: 104

Text #12

Max Range: 0.1357. Min Range: -0.1357

Max Act: 0.0905. Min Act: -0.0002

Data Index: 888633 (C4 (Web Text))

Max Activating Token Index: 849

Text #13

Max Range: 0.1357. Min Range: -0.1357

Max Act: 0.0887. Min Act: -0.0002

Data Index: 1294209 (C4 (Web Text))

Max Activating Token Index: 743

Text #14

Max Range: 0.1357. Min Range: -0.1357

Max Act: 0.0852. Min Act: -0.0002

Data Index: 1350365 (C4 (Web Text))

Max Activating Token Index: 661

Text #15

Max Range: 0.1357. Min Range: -0.1357

Max Act: 0.0870. Min Act: -0.0002

Data Index: 324049 (C4 (Web Text))

Max Activating Token Index: 110

Text #16

Max Range: 0.1357. Min Range: -0.1357

Max Act: 0.0841. Min Act: -0.0002

Data Index: 649256 (C4 (Web Text))

Max Activating Token Index: 139

Text #17

Max Range: 0.1357. Min Range: -0.1357

Max Act: 0.0849. Min Act: -0.0002

Data Index: 1055888 (C4 (Web Text))

Max Activating Token Index: 227

Text #18

Max Range: 0.1357. Min Range: -0.1357

Max Act: 0.0830. Min Act: -0.0002

Data Index: 685301 (C4 (Web Text))

Max Activating Token Index: 225

Text #19

Max Range: 0.1357. Min Range: -0.1357

Max Act: 0.0773. Min Act: -0.0002

Data Index: 83774 (C4 (Web Text))

Max Activating Token Index: 265