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

Dataset: The Pile

Neuron 2948 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5541. Min Range: -0.5541

Max Act: 0.5541. Min Act: -0.0000

Data Index: 370703 (The Pile)

Max Activating Token Index: 121

Text #1

Max Range: 0.5541. Min Range: -0.5541

Max Act: 0.3793. Min Act: -0.0000

Data Index: 1229406 (The Pile)

Max Activating Token Index: 798

Text #2

Max Range: 0.5541. Min Range: -0.5541

Max Act: 0.4028. Min Act: -0.0000

Data Index: 494537 (The Pile)

Max Activating Token Index: 509

Text #3

Max Range: 0.5541. Min Range: -0.5541

Max Act: 0.4144. Min Act: -0.0000

Data Index: 1816278 (The Pile)

Max Activating Token Index: 267

Text #4

Max Range: 0.5541. Min Range: -0.5541

Max Act: 0.3973. Min Act: -0.0000

Data Index: 1456787 (The Pile)

Max Activating Token Index: 869

Text #5

Max Range: 0.5541. Min Range: -0.5541

Max Act: 0.3808. Min Act: -0.0000

Data Index: 1152993 (The Pile)

Max Activating Token Index: 275

Text #6

Max Range: 0.5541. Min Range: -0.5541

Max Act: 0.3681. Min Act: -0.0000

Data Index: 1520515 (The Pile)

Max Activating Token Index: 523

Text #7

Max Range: 0.5541. Min Range: -0.5541

Max Act: 0.3809. Min Act: -0.0000

Data Index: 1235882 (The Pile)

Max Activating Token Index: 753

Text #8

Max Range: 0.5541. Min Range: -0.5541

Max Act: 0.3650. Min Act: -0.0000

Data Index: 633633 (The Pile)

Max Activating Token Index: 42

Text #9

Max Range: 0.5541. Min Range: -0.5541

Max Act: 0.3585. Min Act: -0.0000

Data Index: 1618517 (The Pile)

Max Activating Token Index: 497

Text #10

Max Range: 0.5541. Min Range: -0.5541

Max Act: 0.3719. Min Act: -0.0000

Data Index: 1948601 (The Pile)

Max Activating Token Index: 436

Text #11

Max Range: 0.5541. Min Range: -0.5541

Max Act: 0.3525. Min Act: -0.0000

Data Index: 1230546 (The Pile)

Max Activating Token Index: 700

Text #12

Max Range: 0.5541. Min Range: -0.5541

Max Act: 0.3727. Min Act: -0.0000

Data Index: 285919 (The Pile)

Max Activating Token Index: 171

Text #13

Max Range: 0.5541. Min Range: -0.5541

Max Act: 0.3434. Min Act: -0.0000

Data Index: 9501 (The Pile)

Max Activating Token Index: 992

Text #14

Max Range: 0.5541. Min Range: -0.5541

Max Act: 0.3635. Min Act: -0.0000

Data Index: 420759 (The Pile)

Max Activating Token Index: 632

Text #15

Max Range: 0.5541. Min Range: -0.5541

Max Act: 0.3194. Min Act: -0.0000

Data Index: 486996 (The Pile)

Max Activating Token Index: 12

Text #16

Max Range: 0.5541. Min Range: -0.5541

Max Act: 0.3594. Min Act: -0.0000

Data Index: 332159 (The Pile)

Max Activating Token Index: 498

Text #17

Max Range: 0.5541. Min Range: -0.5541

Max Act: 0.3472. Min Act: -0.0000

Data Index: 931041 (The Pile)

Max Activating Token Index: 575

Text #18

Max Range: 0.5541. Min Range: -0.5541

Max Act: 0.3429. Min Act: -0.0000

Data Index: 1532916 (The Pile)

Max Activating Token Index: 53

Text #19

Max Range: 0.5541. Min Range: -0.5541

Max Act: 0.3398. Min Act: -0.0000

Data Index: 1755126 (The Pile)

Max Activating Token Index: 931