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

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

Neuron 1868 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0000. Min Range: -0.0000

Max Act: 0.0000. Min Act: -0.0002

Data Index: 946367 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.0000. Min Range: -0.0000

Max Act: 0.0000. Min Act: -0.0002

Data Index: 767361 (C4 (Web Text))

Max Activating Token Index: 749

Text #2

Max Range: 0.0000. Min Range: -0.0000

Max Act: 0.0000. Min Act: -0.0002

Data Index: 376553 (C4 (Web Text))

Max Activating Token Index: 481

Text #3

Max Range: 0.0000. Min Range: -0.0000

Max Act: 0.0000. Min Act: -0.0002

Data Index: 24028 (C4 (Web Text))

Max Activating Token Index: 879

Text #4

Max Range: 0.0000. Min Range: -0.0000

Max Act: 0.0000. Min Act: -0.0002

Data Index: 44848 (C4 (Web Text))

Max Activating Token Index: 805

Text #5

Max Range: 0.0000. Min Range: -0.0000

Max Act: 0.0000. Min Act: -0.0002

Data Index: 1311659 (C4 (Web Text))

Max Activating Token Index: 868

Text #6

Max Range: 0.0000. Min Range: -0.0000

Max Act: 0.0000. Min Act: -0.0002

Data Index: 1151091 (C4 (Web Text))

Max Activating Token Index: 981

Text #7

Max Range: 0.0000. Min Range: -0.0000

Max Act: 0.0000. Min Act: -0.0002

Data Index: 1337687 (C4 (Web Text))

Max Activating Token Index: 713

Text #8

Max Range: 0.0000. Min Range: -0.0000

Max Act: 0.0000. Min Act: -0.0002

Data Index: 1064883 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 0.0000. Min Range: -0.0000

Max Act: 0.0000. Min Act: -0.0002

Data Index: 665328 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 0.0000. Min Range: -0.0000

Max Act: 0.0000. Min Act: -0.0002

Data Index: 472044 (C4 (Web Text))

Max Activating Token Index: 863

Text #11

Max Range: 0.0000. Min Range: -0.0000

Max Act: 0.0000. Min Act: -0.0002

Data Index: 271264 (C4 (Web Text))

Max Activating Token Index: 976

Text #12

Max Range: 0.0000. Min Range: -0.0000

Max Act: 0.0000. Min Act: -0.0002

Data Index: 10637 (C4 (Web Text))

Max Activating Token Index: 701

Text #13

Max Range: 0.0000. Min Range: -0.0000

Max Act: 0.0000. Min Act: -0.0002

Data Index: 437049 (C4 (Web Text))

Max Activating Token Index: 683

Text #14

Max Range: 0.0000. Min Range: -0.0000

Max Act: 0.0000. Min Act: -0.0002

Data Index: 916229 (C4 (Web Text))

Max Activating Token Index: 901

Text #15

Max Range: 0.0000. Min Range: -0.0000

Max Act: 0.0000. Min Act: -0.0002

Data Index: 1147115 (C4 (Web Text))

Max Activating Token Index: 932

Text #16

Max Range: 0.0000. Min Range: -0.0000

Max Act: 0.0000. Min Act: -0.0002

Data Index: 617970 (C4 (Web Text))

Max Activating Token Index: 991

Text #17

Max Range: 0.0000. Min Range: -0.0000

Max Act: 0.0000. Min Act: -0.0002

Data Index: 494845 (C4 (Web Text))

Max Activating Token Index: 679

Text #18

Max Range: 0.0000. Min Range: -0.0000

Max Act: -0.0000. Min Act: -0.0002

Data Index: 905935 (C4 (Web Text))

Max Activating Token Index: 973

Text #19

Max Range: 0.0000. Min Range: -0.0000

Max Act: -0.0000. Min Act: -0.0002

Data Index: 1062678 (C4 (Web Text))

Max Activating Token Index: 770