Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3607 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.9838. Min Range: -0.9838

Max Act: 0.9838. Min Act: -0.0000

Data Index: 742211 (C4 (Web Text))

Max Activating Token Index: 866

Text #1

Max Range: 0.9838. Min Range: -0.9838

Max Act: 0.9258. Min Act: -0.0000

Data Index: 203720 (C4 (Web Text))

Max Activating Token Index: 416

Text #2

Max Range: 0.9838. Min Range: -0.9838

Max Act: 0.8840. Min Act: -0.0000

Data Index: 248755 (C4 (Web Text))

Max Activating Token Index: 372

Text #3

Max Range: 0.9838. Min Range: -0.9838

Max Act: 0.8805. Min Act: -0.0000

Data Index: 700728 (C4 (Web Text))

Max Activating Token Index: 613

Text #4

Max Range: 0.9838. Min Range: -0.9838

Max Act: 0.8754. Min Act: 0.0000

Data Index: 291626 (C4 (Web Text))

Max Activating Token Index: 637

Text #5

Max Range: 0.9838. Min Range: -0.9838

Max Act: 0.8413. Min Act: -0.0000

Data Index: 344510 (C4 (Web Text))

Max Activating Token Index: 74

Text #6

Max Range: 0.9838. Min Range: -0.9838

Max Act: 0.8898. Min Act: -0.0000

Data Index: 82168 (C4 (Web Text))

Max Activating Token Index: 985

Text #7

Max Range: 0.9838. Min Range: -0.9838

Max Act: 0.8385. Min Act: -0.0000

Data Index: 357725 (C4 (Web Text))

Max Activating Token Index: 360

Text #8

Max Range: 0.9838. Min Range: -0.9838

Max Act: 0.8251. Min Act: -0.0000

Data Index: 383936 (C4 (Web Text))

Max Activating Token Index: 1004

Text #9

Max Range: 0.9838. Min Range: -0.9838

Max Act: 0.7969. Min Act: -0.0000

Data Index: 965670 (C4 (Web Text))

Max Activating Token Index: 939

Text #10

Max Range: 0.9838. Min Range: -0.9838

Max Act: 0.7896. Min Act: -0.0000

Data Index: 474719 (C4 (Web Text))

Max Activating Token Index: 769

Text #11

Max Range: 0.9838. Min Range: -0.9838

Max Act: 0.7372. Min Act: -0.0000

Data Index: 983009 (C4 (Web Text))

Max Activating Token Index: 603

Text #12

Max Range: 0.9838. Min Range: -0.9838

Max Act: 0.7822. Min Act: -0.0000

Data Index: 756343 (C4 (Web Text))

Max Activating Token Index: 51

Text #13

Max Range: 0.9838. Min Range: -0.9838

Max Act: 0.7762. Min Act: -0.0000

Data Index: 1192820 (C4 (Web Text))

Max Activating Token Index: 74

Text #14

Max Range: 0.9838. Min Range: -0.9838

Max Act: 0.7159. Min Act: -0.0000

Data Index: 459091 (C4 (Web Text))

Max Activating Token Index: 394

Text #15

Max Range: 0.9838. Min Range: -0.9838

Max Act: 0.7569. Min Act: -0.0000

Data Index: 286006 (C4 (Web Text))

Max Activating Token Index: 576

Text #16

Max Range: 0.9838. Min Range: -0.9838

Max Act: 0.8065. Min Act: -0.0000

Data Index: 251341 (C4 (Web Text))

Max Activating Token Index: 539

Text #17

Max Range: 0.9838. Min Range: -0.9838

Max Act: 0.7535. Min Act: -0.0000

Data Index: 1164992 (C4 (Web Text))

Max Activating Token Index: 557

Text #18

Max Range: 0.9838. Min Range: -0.9838

Max Act: 0.8042. Min Act: -0.0000

Data Index: 693854 (C4 (Web Text))

Max Activating Token Index: 805

Text #19

Max Range: 0.9838. Min Range: -0.9838

Max Act: 0.6993. Min Act: -0.0000

Data Index: 191505 (C4 (Web Text))

Max Activating Token Index: 835