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

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

Neuron 4195 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9274. Min Range: -1.9274

Max Act: 1.9252. Min Act: -0.0000

Data Index: 672562 (C4 (Web Text))

Max Activating Token Index: 40

Text #1

Max Range: 1.9274. Min Range: -1.9274

Max Act: 1.9274. Min Act: -0.0000

Data Index: 78097 (C4 (Web Text))

Max Activating Token Index: 789

Text #2

Max Range: 1.9274. Min Range: -1.9274

Max Act: 1.7692. Min Act: -0.0000

Data Index: 173689 (C4 (Web Text))

Max Activating Token Index: 102

Text #3

Max Range: 1.9274. Min Range: -1.9274

Max Act: 1.8483. Min Act: -0.0000

Data Index: 798840 (C4 (Web Text))

Max Activating Token Index: 811

Text #4

Max Range: 1.9274. Min Range: -1.9274

Max Act: 1.8387. Min Act: -0.0000

Data Index: 943156 (C4 (Web Text))

Max Activating Token Index: 879

Text #5

Max Range: 1.9274. Min Range: -1.9274

Max Act: 1.8219. Min Act: -0.0000

Data Index: 642841 (C4 (Web Text))

Max Activating Token Index: 175

Text #6

Max Range: 1.9274. Min Range: -1.9274

Max Act: 1.7722. Min Act: -0.0000

Data Index: 118693 (C4 (Web Text))

Max Activating Token Index: 1022

Text #7

Max Range: 1.9274. Min Range: -1.9274

Max Act: 1.7384. Min Act: -0.0000

Data Index: 1091794 (C4 (Web Text))

Max Activating Token Index: 88

Text #8

Max Range: 1.9274. Min Range: -1.9274

Max Act: 1.7173. Min Act: -0.0000

Data Index: 1024452 (C4 (Web Text))

Max Activating Token Index: 909

Text #9

Max Range: 1.9274. Min Range: -1.9274

Max Act: 1.7168. Min Act: -0.0000

Data Index: 633197 (C4 (Web Text))

Max Activating Token Index: 782

Text #10

Max Range: 1.9274. Min Range: -1.9274

Max Act: 1.7936. Min Act: -0.0000

Data Index: 312396 (C4 (Web Text))

Max Activating Token Index: 1020

Text #11

Max Range: 1.9274. Min Range: -1.9274

Max Act: 1.7589. Min Act: -0.0000

Data Index: 316787 (C4 (Web Text))

Max Activating Token Index: 466

Text #12

Max Range: 1.9274. Min Range: -1.9274

Max Act: 1.6630. Min Act: -0.0000

Data Index: 1102086 (C4 (Web Text))

Max Activating Token Index: 988

Text #13

Max Range: 1.9274. Min Range: -1.9274

Max Act: 1.6475. Min Act: -0.0000

Data Index: 1205123 (C4 (Web Text))

Max Activating Token Index: 114

Text #14

Max Range: 1.9274. Min Range: -1.9274

Max Act: 1.6262. Min Act: -0.0000

Data Index: 507644 (C4 (Web Text))

Max Activating Token Index: 728

Text #15

Max Range: 1.9274. Min Range: -1.9274

Max Act: 1.6122. Min Act: -0.0000

Data Index: 961545 (C4 (Web Text))

Max Activating Token Index: 930

Text #16

Max Range: 1.9274. Min Range: -1.9274

Max Act: 1.6035. Min Act: -0.0000

Data Index: 397476 (C4 (Web Text))

Max Activating Token Index: 694

Text #17

Max Range: 1.9274. Min Range: -1.9274

Max Act: 1.6581. Min Act: -0.0000

Data Index: 371457 (C4 (Web Text))

Max Activating Token Index: 719

Text #18

Max Range: 1.9274. Min Range: -1.9274

Max Act: 1.5388. Min Act: -0.0000

Data Index: 322460 (C4 (Web Text))

Max Activating Token Index: 351

Text #19

Max Range: 1.9274. Min Range: -1.9274

Max Act: 1.5293. Min Act: -0.0000

Data Index: 691353 (C4 (Web Text))

Max Activating Token Index: 743