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

Dataset: The Pile

Neuron 1302 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9648. Min Range: -0.9648

Max Act: 0.9648. Min Act: -0.0000

Data Index: 767403 (The Pile)

Max Activating Token Index: 429

Text #1

Max Range: 0.9648. Min Range: -0.9648

Max Act: 0.6960. Min Act: -0.0000

Data Index: 497883 (The Pile)

Max Activating Token Index: 531

Text #2

Max Range: 0.9648. Min Range: -0.9648

Max Act: 0.6854. Min Act: -0.0000

Data Index: 1869337 (The Pile)

Max Activating Token Index: 869

Text #3

Max Range: 0.9648. Min Range: -0.9648

Max Act: 0.6355. Min Act: -0.0000

Data Index: 181002 (The Pile)

Max Activating Token Index: 462

Text #4

Max Range: 0.9648. Min Range: -0.9648

Max Act: 0.6357. Min Act: -0.0000

Data Index: 1973766 (The Pile)

Max Activating Token Index: 606

Text #5

Max Range: 0.9648. Min Range: -0.9648

Max Act: 0.6381. Min Act: -0.0000

Data Index: 210605 (The Pile)

Max Activating Token Index: 719

Text #6

Max Range: 0.9648. Min Range: -0.9648

Max Act: 0.6470. Min Act: -0.0000

Data Index: 877562 (The Pile)

Max Activating Token Index: 477

Text #7

Max Range: 0.9648. Min Range: -0.9648

Max Act: 0.6067. Min Act: -0.0000

Data Index: 249165 (The Pile)

Max Activating Token Index: 1019

Text #8

Max Range: 0.9648. Min Range: -0.9648

Max Act: 0.6080. Min Act: -0.0000

Data Index: 178705 (The Pile)

Max Activating Token Index: 638

Text #9

Max Range: 0.9648. Min Range: -0.9648

Max Act: 0.6494. Min Act: -0.0000

Data Index: 1874838 (The Pile)

Max Activating Token Index: 805

Text #10

Max Range: 0.9648. Min Range: -0.9648

Max Act: 0.5464. Min Act: -0.0000

Data Index: 760266 (The Pile)

Max Activating Token Index: 157

Text #11

Max Range: 0.9648. Min Range: -0.9648

Max Act: 0.5269. Min Act: -0.0000

Data Index: 341720 (The Pile)

Max Activating Token Index: 301

Text #12

Max Range: 0.9648. Min Range: -0.9648

Max Act: 0.5664. Min Act: -0.0000

Data Index: 1917876 (The Pile)

Max Activating Token Index: 1014

Text #13

Max Range: 0.9648. Min Range: -0.9648

Max Act: 0.6268. Min Act: -0.0000

Data Index: 1851314 (The Pile)

Max Activating Token Index: 545

Text #14

Max Range: 0.9648. Min Range: -0.9648

Max Act: 0.5422. Min Act: -0.0000

Data Index: 1551703 (The Pile)

Max Activating Token Index: 869

Text #15

Max Range: 0.9648. Min Range: -0.9648

Max Act: 0.5488. Min Act: -0.0000

Data Index: 745908 (The Pile)

Max Activating Token Index: 739

Text #16

Max Range: 0.9648. Min Range: -0.9648

Max Act: 0.4775. Min Act: -0.0000

Data Index: 751464 (The Pile)

Max Activating Token Index: 878

Text #17

Max Range: 0.9648. Min Range: -0.9648

Max Act: 0.5467. Min Act: -0.0000

Data Index: 578799 (The Pile)

Max Activating Token Index: 881

Text #18

Max Range: 0.9648. Min Range: -0.9648

Max Act: 0.5101. Min Act: -0.0000

Data Index: 510432 (The Pile)

Max Activating Token Index: 651

Text #19

Max Range: 0.9648. Min Range: -0.9648

Max Act: 0.5269. Min Act: -0.0000

Data Index: 1073503 (The Pile)

Max Activating Token Index: 621