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

Dataset: The Pile

Neuron 1774 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: 0.1636. Min Range: -0.1636

Max Act: 0.1636. Min Act: -0.0000

Data Index: 1709261 (The Pile)

Max Activating Token Index: 430

Text #1

Max Range: 0.1636. Min Range: -0.1636

Max Act: 0.1246. Min Act: -0.0000

Data Index: 654147 (The Pile)

Max Activating Token Index: 982

Text #2

Max Range: 0.1636. Min Range: -0.1636

Max Act: 0.1014. Min Act: -0.0000

Data Index: 155618 (The Pile)

Max Activating Token Index: 183

Text #3

Max Range: 0.1636. Min Range: -0.1636

Max Act: 0.0986. Min Act: -0.0000

Data Index: 1018631 (The Pile)

Max Activating Token Index: 638

Text #4

Max Range: 0.1636. Min Range: -0.1636

Max Act: 0.1045. Min Act: -0.0000

Data Index: 1312130 (The Pile)

Max Activating Token Index: 170

Text #5

Max Range: 0.1636. Min Range: -0.1636

Max Act: 0.1001. Min Act: -0.0000

Data Index: 1908349 (The Pile)

Max Activating Token Index: 769

Text #6

Max Range: 0.1636. Min Range: -0.1636

Max Act: 0.0986. Min Act: -0.0000

Data Index: 162606 (The Pile)

Max Activating Token Index: 583

Text #7

Max Range: 0.1636. Min Range: -0.1636

Max Act: 0.0978. Min Act: -0.0000

Data Index: 1169530 (The Pile)

Max Activating Token Index: 46

Text #8

Max Range: 0.1636. Min Range: -0.1636

Max Act: 0.1007. Min Act: -0.0000

Data Index: 1224996 (The Pile)

Max Activating Token Index: 247

Text #9

Max Range: 0.1636. Min Range: -0.1636

Max Act: 0.1004. Min Act: -0.0000

Data Index: 664717 (The Pile)

Max Activating Token Index: 719

Text #10

Max Range: 0.1636. Min Range: -0.1636

Max Act: 0.0943. Min Act: -0.0000

Data Index: 1283079 (The Pile)

Max Activating Token Index: 1018

Text #11

Max Range: 0.1636. Min Range: -0.1636

Max Act: 0.0792. Min Act: -0.0000

Data Index: 1780790 (The Pile)

Max Activating Token Index: 609

Text #12

Max Range: 0.1636. Min Range: -0.1636

Max Act: 0.0901. Min Act: -0.0000

Data Index: 1390346 (The Pile)

Max Activating Token Index: 300

Text #13

Max Range: 0.1636. Min Range: -0.1636

Max Act: 0.0895. Min Act: -0.0000

Data Index: 529678 (The Pile)

Max Activating Token Index: 382

Text #14

Max Range: 0.1636. Min Range: -0.1636

Max Act: 0.0894. Min Act: -0.0000

Data Index: 489126 (The Pile)

Max Activating Token Index: 302

Text #15

Max Range: 0.1636. Min Range: -0.1636

Max Act: 0.0939. Min Act: -0.0000

Data Index: 1844070 (The Pile)

Max Activating Token Index: 868

Text #16

Max Range: 0.1636. Min Range: -0.1636

Max Act: 0.0815. Min Act: -0.0000

Data Index: 300223 (The Pile)

Max Activating Token Index: 810

Text #17

Max Range: 0.1636. Min Range: -0.1636

Max Act: 0.0859. Min Act: -0.0000

Data Index: 57995 (The Pile)

Max Activating Token Index: 613

Text #18

Max Range: 0.1636. Min Range: -0.1636

Max Act: 0.0890. Min Act: -0.0000

Data Index: 1842887 (The Pile)

Max Activating Token Index: 197

Text #19

Max Range: 0.1636. Min Range: -0.1636

Max Act: 0.0916. Min Act: -0.0000

Data Index: 147522 (The Pile)

Max Activating Token Index: 976