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

Dataset: The Pile

Neuron 152 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6960. Min Range: -1.6960

Max Act: 1.6206. Min Act: -0.0000

Data Index: 425552 (The Pile)

Max Activating Token Index: 811

Text #1

Max Range: 1.6960. Min Range: -1.6960

Max Act: 1.6887. Min Act: -0.0000

Data Index: 1320740 (The Pile)

Max Activating Token Index: 482

Text #2

Max Range: 1.6960. Min Range: -1.6960

Max Act: 1.6960. Min Act: -0.0000

Data Index: 1262073 (The Pile)

Max Activating Token Index: 593

Text #3

Max Range: 1.6960. Min Range: -1.6960

Max Act: 1.3970. Min Act: -0.0000

Data Index: 397711 (The Pile)

Max Activating Token Index: 724

Text #4

Max Range: 1.6960. Min Range: -1.6960

Max Act: 1.4534. Min Act: -0.0000

Data Index: 24631 (The Pile)

Max Activating Token Index: 450

Text #5

Max Range: 1.6960. Min Range: -1.6960

Max Act: 1.6331. Min Act: -0.0000

Data Index: 74141 (The Pile)

Max Activating Token Index: 701

Text #6

Max Range: 1.6960. Min Range: -1.6960

Max Act: 1.4679. Min Act: -0.0000

Data Index: 1904673 (The Pile)

Max Activating Token Index: 82

Text #7

Max Range: 1.6960. Min Range: -1.6960

Max Act: 1.3983. Min Act: -0.0000

Data Index: 397168 (The Pile)

Max Activating Token Index: 805

Text #8

Max Range: 1.6960. Min Range: -1.6960

Max Act: 1.6093. Min Act: -0.0000

Data Index: 1533387 (The Pile)

Max Activating Token Index: 750

Text #9

Max Range: 1.6960. Min Range: -1.6960

Max Act: 1.4407. Min Act: -0.0000

Data Index: 1827561 (The Pile)

Max Activating Token Index: 848

Text #10

Max Range: 1.6960. Min Range: -1.6960

Max Act: 1.1451. Min Act: -0.0000

Data Index: 408554 (The Pile)

Max Activating Token Index: 935

Text #11

Max Range: 1.6960. Min Range: -1.6960

Max Act: 1.1511. Min Act: -0.0000

Data Index: 1860408 (The Pile)

Max Activating Token Index: 845

Text #12

Max Range: 1.6960. Min Range: -1.6960

Max Act: 1.3382. Min Act: -0.0000

Data Index: 817370 (The Pile)

Max Activating Token Index: 579

Text #13

Max Range: 1.6960. Min Range: -1.6960

Max Act: 1.0469. Min Act: -0.0000

Data Index: 258669 (The Pile)

Max Activating Token Index: 182

Text #14

Max Range: 1.6960. Min Range: -1.6960

Max Act: 1.2347. Min Act: -0.0000

Data Index: 1586593 (The Pile)

Max Activating Token Index: 362

Text #15

Max Range: 1.6960. Min Range: -1.6960

Max Act: 1.1755. Min Act: -0.0000

Data Index: 955935 (The Pile)

Max Activating Token Index: 252

Text #16

Max Range: 1.6960. Min Range: -1.6960

Max Act: 1.2237. Min Act: -0.0000

Data Index: 1937940 (The Pile)

Max Activating Token Index: 1019

Text #17

Max Range: 1.6960. Min Range: -1.6960

Max Act: 1.2279. Min Act: -0.0000

Data Index: 1290993 (The Pile)

Max Activating Token Index: 358

Text #18

Max Range: 1.6960. Min Range: -1.6960

Max Act: 1.2111. Min Act: -0.0000

Data Index: 1552559 (The Pile)

Max Activating Token Index: 1009

Text #19

Max Range: 1.6960. Min Range: -1.6960

Max Act: 1.2051. Min Act: -0.0000

Data Index: 1379431 (The Pile)

Max Activating Token Index: 173