Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 3989 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.4728. Min Range: -0.4728

Max Act: 0.4728. Min Act: -0.0000

Data Index: 1125596 (The Pile)

Max Activating Token Index: 837

Text #1

Max Range: 0.4728. Min Range: -0.4728

Max Act: 0.3915. Min Act: -0.0000

Data Index: 880300 (The Pile)

Max Activating Token Index: 990

Text #2

Max Range: 0.4728. Min Range: -0.4728

Max Act: 0.4184. Min Act: -0.0000

Data Index: 265444 (The Pile)

Max Activating Token Index: 77

Text #3

Max Range: 0.4728. Min Range: -0.4728

Max Act: 0.3728. Min Act: -0.0000

Data Index: 1704585 (The Pile)

Max Activating Token Index: 858

Text #4

Max Range: 0.4728. Min Range: -0.4728

Max Act: 0.3802. Min Act: -0.0000

Data Index: 1627587 (The Pile)

Max Activating Token Index: 313

Text #5

Max Range: 0.4728. Min Range: -0.4728

Max Act: 0.3674. Min Act: -0.0000

Data Index: 1711921 (The Pile)

Max Activating Token Index: 324

Text #6

Max Range: 0.4728. Min Range: -0.4728

Max Act: 0.3305. Min Act: -0.0000

Data Index: 612583 (The Pile)

Max Activating Token Index: 844

Text #7

Max Range: 0.4728. Min Range: -0.4728

Max Act: 0.3212. Min Act: -0.0000

Data Index: 758965 (The Pile)

Max Activating Token Index: 590

Text #8

Max Range: 0.4728. Min Range: -0.4728

Max Act: 0.3787. Min Act: -0.0000

Data Index: 140257 (The Pile)

Max Activating Token Index: 701

Text #9

Max Range: 0.4728. Min Range: -0.4728

Max Act: 0.3493. Min Act: -0.0000

Data Index: 1247745 (The Pile)

Max Activating Token Index: 284

Text #10

Max Range: 0.4728. Min Range: -0.4728

Max Act: 0.3530. Min Act: -0.0000

Data Index: 1933324 (The Pile)

Max Activating Token Index: 322

Text #11

Max Range: 0.4728. Min Range: -0.4728

Max Act: 0.3859. Min Act: -0.0000

Data Index: 612933 (The Pile)

Max Activating Token Index: 556

Text #12

Max Range: 0.4728. Min Range: -0.4728

Max Act: 0.3598. Min Act: -0.0000

Data Index: 577743 (The Pile)

Max Activating Token Index: 357

Text #13

Max Range: 0.4728. Min Range: -0.4728

Max Act: 0.3358. Min Act: -0.0000

Data Index: 87400 (The Pile)

Max Activating Token Index: 61

Text #14

Max Range: 0.4728. Min Range: -0.4728

Max Act: 0.3294. Min Act: -0.0000

Data Index: 272841 (The Pile)

Max Activating Token Index: 27

Text #15

Max Range: 0.4728. Min Range: -0.4728

Max Act: 0.3611. Min Act: -0.0000

Data Index: 598022 (The Pile)

Max Activating Token Index: 856

Text #16

Max Range: 0.4728. Min Range: -0.4728

Max Act: 0.3444. Min Act: -0.0000

Data Index: 1662066 (The Pile)

Max Activating Token Index: 329

Text #17

Max Range: 0.4728. Min Range: -0.4728

Max Act: 0.2919. Min Act: -0.0000

Data Index: 1477936 (The Pile)

Max Activating Token Index: 792

Text #18

Max Range: 0.4728. Min Range: -0.4728

Max Act: 0.3420. Min Act: -0.0000

Data Index: 364828 (The Pile)

Max Activating Token Index: 728

Text #19

Max Range: 0.4728. Min Range: -0.4728

Max Act: 0.3305. Min Act: -0.0000

Data Index: 1119519 (The Pile)

Max Activating Token Index: 504