Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 511 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.9334. Min Range: -0.9334

Max Act: 0.9334. Min Act: -0.0000

Data Index: 694708 (The Pile)

Max Activating Token Index: 836

Text #1

Max Range: 0.9334. Min Range: -0.9334

Max Act: 0.7986. Min Act: -0.0000

Data Index: 687035 (The Pile)

Max Activating Token Index: 164

Text #2

Max Range: 0.9334. Min Range: -0.9334

Max Act: 0.7193. Min Act: -0.0000

Data Index: 1794336 (The Pile)

Max Activating Token Index: 854

Text #3

Max Range: 0.9334. Min Range: -0.9334

Max Act: 0.8263. Min Act: -0.0000

Data Index: 1244110 (The Pile)

Max Activating Token Index: 890

Text #4

Max Range: 0.9334. Min Range: -0.9334

Max Act: 0.7648. Min Act: -0.0000

Data Index: 579782 (The Pile)

Max Activating Token Index: 445

Text #5

Max Range: 0.9334. Min Range: -0.9334

Max Act: 0.8220. Min Act: -0.0000

Data Index: 775013 (The Pile)

Max Activating Token Index: 851

Text #6

Max Range: 0.9334. Min Range: -0.9334

Max Act: 0.7563. Min Act: -0.0000

Data Index: 1349587 (The Pile)

Max Activating Token Index: 879

Text #7

Max Range: 0.9334. Min Range: -0.9334

Max Act: 0.8190. Min Act: -0.0000

Data Index: 1573318 (The Pile)

Max Activating Token Index: 291

Text #8

Max Range: 0.9334. Min Range: -0.9334

Max Act: 0.7637. Min Act: -0.0000

Data Index: 460449 (The Pile)

Max Activating Token Index: 952

Text #9

Max Range: 0.9334. Min Range: -0.9334

Max Act: 0.8198. Min Act: -0.0000

Data Index: 595975 (The Pile)

Max Activating Token Index: 720

Text #10

Max Range: 0.9334. Min Range: -0.9334

Max Act: 0.7600. Min Act: -0.0000

Data Index: 928286 (The Pile)

Max Activating Token Index: 276

Text #11

Max Range: 0.9334. Min Range: -0.9334

Max Act: 0.6418. Min Act: -0.0000

Data Index: 766699 (The Pile)

Max Activating Token Index: 652

Text #12

Max Range: 0.9334. Min Range: -0.9334

Max Act: 0.7625. Min Act: -0.0000

Data Index: 651135 (The Pile)

Max Activating Token Index: 638

Text #13

Max Range: 0.9334. Min Range: -0.9334

Max Act: 0.7455. Min Act: -0.0000

Data Index: 600937 (The Pile)

Max Activating Token Index: 972

Text #14

Max Range: 0.9334. Min Range: -0.9334

Max Act: 0.7942. Min Act: -0.0000

Data Index: 1969757 (The Pile)

Max Activating Token Index: 160

Text #15

Max Range: 0.9334. Min Range: -0.9334

Max Act: 0.7204. Min Act: -0.0000

Data Index: 236898 (The Pile)

Max Activating Token Index: 728

Text #16

Max Range: 0.9334. Min Range: -0.9334

Max Act: 0.7385. Min Act: -0.0000

Data Index: 566017 (The Pile)

Max Activating Token Index: 469

Text #17

Max Range: 0.9334. Min Range: -0.9334

Max Act: 0.7814. Min Act: -0.0000

Data Index: 1649260 (The Pile)

Max Activating Token Index: 829

Text #18

Max Range: 0.9334. Min Range: -0.9334

Max Act: 0.7935. Min Act: -0.0000

Data Index: 722044 (The Pile)

Max Activating Token Index: 711

Text #19

Max Range: 0.9334. Min Range: -0.9334

Max Act: 0.6850. Min Act: -0.0000

Data Index: 1844090 (The Pile)

Max Activating Token Index: 481