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

Dataset: The Pile

Neuron 2457 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1999. Min Range: -2.1999

Max Act: 2.1999. Min Act: -0.0000

Data Index: 844755 (The Pile)

Max Activating Token Index: 353

Text #1

Max Range: 2.1999. Min Range: -2.1999

Max Act: 2.0025. Min Act: -0.0000

Data Index: 897400 (The Pile)

Max Activating Token Index: 246

Text #2

Max Range: 2.1999. Min Range: -2.1999

Max Act: 1.7008. Min Act: -0.0000

Data Index: 419674 (The Pile)

Max Activating Token Index: 584

Text #3

Max Range: 2.1999. Min Range: -2.1999

Max Act: 1.5606. Min Act: -0.0000

Data Index: 1674625 (The Pile)

Max Activating Token Index: 1004

Text #4

Max Range: 2.1999. Min Range: -2.1999

Max Act: 1.6878. Min Act: -0.0000

Data Index: 1162285 (The Pile)

Max Activating Token Index: 293

Text #5

Max Range: 2.1999. Min Range: -2.1999

Max Act: 1.3784. Min Act: -0.0000

Data Index: 507369 (The Pile)

Max Activating Token Index: 768

Text #6

Max Range: 2.1999. Min Range: -2.1999

Max Act: 1.6480. Min Act: -0.0000

Data Index: 1156824 (The Pile)

Max Activating Token Index: 320

Text #7

Max Range: 2.1999. Min Range: -2.1999

Max Act: 1.7354. Min Act: -0.0000

Data Index: 732405 (The Pile)

Max Activating Token Index: 728

Text #8

Max Range: 2.1999. Min Range: -2.1999

Max Act: 1.5768. Min Act: -0.0000

Data Index: 1606544 (The Pile)

Max Activating Token Index: 931

Text #9

Max Range: 2.1999. Min Range: -2.1999

Max Act: 1.5325. Min Act: -0.0000

Data Index: 1360445 (The Pile)

Max Activating Token Index: 665

Text #10

Max Range: 2.1999. Min Range: -2.1999

Max Act: 1.5693. Min Act: -0.0000

Data Index: 811409 (The Pile)

Max Activating Token Index: 859

Text #11

Max Range: 2.1999. Min Range: -2.1999

Max Act: 1.6919. Min Act: -0.0000

Data Index: 1893328 (The Pile)

Max Activating Token Index: 1011

Text #12

Max Range: 2.1999. Min Range: -2.1999

Max Act: 1.4739. Min Act: -0.0000

Data Index: 746708 (The Pile)

Max Activating Token Index: 71

Text #13

Max Range: 2.1999. Min Range: -2.1999

Max Act: 1.4639. Min Act: -0.0000

Data Index: 474583 (The Pile)

Max Activating Token Index: 936

Text #14

Max Range: 2.1999. Min Range: -2.1999

Max Act: 1.5409. Min Act: -0.0000

Data Index: 990374 (The Pile)

Max Activating Token Index: 250

Text #15

Max Range: 2.1999. Min Range: -2.1999

Max Act: 1.6290. Min Act: -0.0000

Data Index: 427807 (The Pile)

Max Activating Token Index: 457

Text #16

Max Range: 2.1999. Min Range: -2.1999

Max Act: 1.5048. Min Act: -0.0000

Data Index: 672415 (The Pile)

Max Activating Token Index: 53

Text #17

Max Range: 2.1999. Min Range: -2.1999

Max Act: 1.5096. Min Act: -0.0000

Data Index: 512058 (The Pile)

Max Activating Token Index: 64

Text #18

Max Range: 2.1999. Min Range: -2.1999

Max Act: 1.5987. Min Act: -0.0000

Data Index: 766214 (The Pile)

Max Activating Token Index: 995

Text #19

Max Range: 2.1999. Min Range: -2.1999

Max Act: 1.7529. Min Act: -0.0000

Data Index: 387362 (The Pile)

Max Activating Token Index: 824