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

Dataset: The Pile

Neuron 4202 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: 1.0567. Min Range: -1.0567

Max Act: 0.9357. Min Act: -0.0000

Data Index: 877115 (The Pile)

Max Activating Token Index: 636

Text #1

Max Range: 1.0567. Min Range: -1.0567

Max Act: 0.9141. Min Act: -0.0000

Data Index: 572531 (The Pile)

Max Activating Token Index: 637

Text #2

Max Range: 1.0567. Min Range: -1.0567

Max Act: 0.8300. Min Act: -0.0000

Data Index: 675488 (The Pile)

Max Activating Token Index: 792

Text #3

Max Range: 1.0567. Min Range: -1.0567

Max Act: 0.8728. Min Act: -0.0000

Data Index: 641746 (The Pile)

Max Activating Token Index: 531

Text #4

Max Range: 1.0567. Min Range: -1.0567

Max Act: 1.0567. Min Act: -0.0000

Data Index: 1203563 (The Pile)

Max Activating Token Index: 393

Text #5

Max Range: 1.0567. Min Range: -1.0567

Max Act: 0.8471. Min Act: -0.0000

Data Index: 1893328 (The Pile)

Max Activating Token Index: 668

Text #6

Max Range: 1.0567. Min Range: -1.0567

Max Act: 0.9299. Min Act: -0.0000

Data Index: 308501 (The Pile)

Max Activating Token Index: 410

Text #7

Max Range: 1.0567. Min Range: -1.0567

Max Act: 0.8408. Min Act: -0.0000

Data Index: 17057 (The Pile)

Max Activating Token Index: 256

Text #8

Max Range: 1.0567. Min Range: -1.0567

Max Act: 0.8457. Min Act: -0.0000

Data Index: 396580 (The Pile)

Max Activating Token Index: 252

Text #9

Max Range: 1.0567. Min Range: -1.0567

Max Act: 0.8954. Min Act: -0.0000

Data Index: 1647411 (The Pile)

Max Activating Token Index: 617

Text #10

Max Range: 1.0567. Min Range: -1.0567

Max Act: 0.9091. Min Act: -0.0000

Data Index: 1606544 (The Pile)

Max Activating Token Index: 536

Text #11

Max Range: 1.0567. Min Range: -1.0567

Max Act: 0.7589. Min Act: -0.0000

Data Index: 68165 (The Pile)

Max Activating Token Index: 558

Text #12

Max Range: 1.0567. Min Range: -1.0567

Max Act: 0.8868. Min Act: -0.0000

Data Index: 466701 (The Pile)

Max Activating Token Index: 576

Text #13

Max Range: 1.0567. Min Range: -1.0567

Max Act: 0.9039. Min Act: -0.0000

Data Index: 1418493 (The Pile)

Max Activating Token Index: 240

Text #14

Max Range: 1.0567. Min Range: -1.0567

Max Act: 0.7166. Min Act: -0.0000

Data Index: 221962 (The Pile)

Max Activating Token Index: 726

Text #15

Max Range: 1.0567. Min Range: -1.0567

Max Act: 0.8496. Min Act: -0.0000

Data Index: 355632 (The Pile)

Max Activating Token Index: 753

Text #16

Max Range: 1.0567. Min Range: -1.0567

Max Act: 0.9418. Min Act: -0.0000

Data Index: 251840 (The Pile)

Max Activating Token Index: 370

Text #17

Max Range: 1.0567. Min Range: -1.0567

Max Act: 0.6942. Min Act: -0.0000

Data Index: 1079439 (The Pile)

Max Activating Token Index: 737

Text #18

Max Range: 1.0567. Min Range: -1.0567

Max Act: 0.8458. Min Act: -0.0000

Data Index: 282339 (The Pile)

Max Activating Token Index: 479

Text #19

Max Range: 1.0567. Min Range: -1.0567

Max Act: 0.8025. Min Act: -0.0000

Data Index: 144889 (The Pile)

Max Activating Token Index: 175