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

Dataset: The Pile

Neuron 1492 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: 0.8895. Min Range: -0.8895

Max Act: 0.8895. Min Act: -0.0000

Data Index: 1419312 (The Pile)

Max Activating Token Index: 742

Text #1

Max Range: 0.8895. Min Range: -0.8895

Max Act: 0.7709. Min Act: -0.0000

Data Index: 733336 (The Pile)

Max Activating Token Index: 978

Text #2

Max Range: 0.8895. Min Range: -0.8895

Max Act: 0.7258. Min Act: -0.0000

Data Index: 575576 (The Pile)

Max Activating Token Index: 946

Text #3

Max Range: 0.8895. Min Range: -0.8895

Max Act: 0.7465. Min Act: -0.0000

Data Index: 444593 (The Pile)

Max Activating Token Index: 481

Text #4

Max Range: 0.8895. Min Range: -0.8895

Max Act: 0.7295. Min Act: -0.0000

Data Index: 694064 (The Pile)

Max Activating Token Index: 997

Text #5

Max Range: 0.8895. Min Range: -0.8895

Max Act: 0.7476. Min Act: -0.0000

Data Index: 1003381 (The Pile)

Max Activating Token Index: 162

Text #6

Max Range: 0.8895. Min Range: -0.8895

Max Act: 0.7121. Min Act: -0.0000

Data Index: 377275 (The Pile)

Max Activating Token Index: 279

Text #7

Max Range: 0.8895. Min Range: -0.8895

Max Act: 0.6921. Min Act: -0.0000

Data Index: 816220 (The Pile)

Max Activating Token Index: 886

Text #8

Max Range: 0.8895. Min Range: -0.8895

Max Act: 0.7072. Min Act: -0.0000

Data Index: 1550727 (The Pile)

Max Activating Token Index: 317

Text #9

Max Range: 0.8895. Min Range: -0.8895

Max Act: 0.6779. Min Act: -0.0000

Data Index: 162315 (The Pile)

Max Activating Token Index: 94

Text #10

Max Range: 0.8895. Min Range: -0.8895

Max Act: 0.6009. Min Act: -0.0000

Data Index: 1909802 (The Pile)

Max Activating Token Index: 668

Text #11

Max Range: 0.8895. Min Range: -0.8895

Max Act: 0.7988. Min Act: -0.0000

Data Index: 1975600 (The Pile)

Max Activating Token Index: 947

Text #12

Max Range: 0.8895. Min Range: -0.8895

Max Act: 0.7180. Min Act: -0.0000

Data Index: 1425705 (The Pile)

Max Activating Token Index: 784

Text #13

Max Range: 0.8895. Min Range: -0.8895

Max Act: 0.6621. Min Act: -0.0000

Data Index: 1188203 (The Pile)

Max Activating Token Index: 411

Text #14

Max Range: 0.8895. Min Range: -0.8895

Max Act: 0.6342. Min Act: -0.0000

Data Index: 1292280 (The Pile)

Max Activating Token Index: 278

Text #15

Max Range: 0.8895. Min Range: -0.8895

Max Act: 0.5973. Min Act: -0.0000

Data Index: 715468 (The Pile)

Max Activating Token Index: 637

Text #16

Max Range: 0.8895. Min Range: -0.8895

Max Act: 0.5564. Min Act: -0.0000

Data Index: 597589 (The Pile)

Max Activating Token Index: 144

Text #17

Max Range: 0.8895. Min Range: -0.8895

Max Act: 0.5238. Min Act: -0.0000

Data Index: 1664621 (The Pile)

Max Activating Token Index: 477

Text #18

Max Range: 0.8895. Min Range: -0.8895

Max Act: 0.5416. Min Act: -0.0000

Data Index: 1665054 (The Pile)

Max Activating Token Index: 470

Text #19

Max Range: 0.8895. Min Range: -0.8895

Max Act: 0.6730. Min Act: -0.0000

Data Index: 726628 (The Pile)

Max Activating Token Index: 700