Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

Dataset: The Pile

Neuron 105 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l-pile')

Text #0

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.1021. Min Act: -0.0001

Data Index: 1036711 (The Pile)

Max Activating Token Index: 387

Text #1

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.1007. Min Act: -0.0001

Data Index: 715383 (The Pile)

Max Activating Token Index: 553

Text #2

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0933. Min Act: -0.0000

Data Index: 990607 (The Pile)

Max Activating Token Index: 558

Text #3

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0762. Min Act: -0.0000

Data Index: 1415234 (The Pile)

Max Activating Token Index: 838

Text #4

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0731. Min Act: -0.0001

Data Index: 1350302 (The Pile)

Max Activating Token Index: 674

Text #5

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0732. Min Act: -0.0000

Data Index: 33015 (The Pile)

Max Activating Token Index: 297

Text #6

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0745. Min Act: -0.0000

Data Index: 995796 (The Pile)

Max Activating Token Index: 560

Text #7

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0719. Min Act: -0.0001

Data Index: 1272762 (The Pile)

Max Activating Token Index: 552

Text #8

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0704. Min Act: -0.0000

Data Index: 371764 (The Pile)

Max Activating Token Index: 519

Text #9

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0682. Min Act: -0.0000

Data Index: 747506 (The Pile)

Max Activating Token Index: 915

Text #10

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0711. Min Act: -0.0000

Data Index: 675493 (The Pile)

Max Activating Token Index: 1019

Text #11

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0632. Min Act: -0.0001

Data Index: 1502867 (The Pile)

Max Activating Token Index: 894

Text #12

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0565. Min Act: -0.0001

Data Index: 1633775 (The Pile)

Max Activating Token Index: 850

Text #13

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0628. Min Act: -0.0001

Data Index: 1789392 (The Pile)

Max Activating Token Index: 503

Text #14

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0649. Min Act: -0.0001

Data Index: 124116 (The Pile)

Max Activating Token Index: 415

Text #15

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0596. Min Act: -0.0001

Data Index: 1495452 (The Pile)

Max Activating Token Index: 674

Text #16

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0607. Min Act: -0.0001

Data Index: 1197032 (The Pile)

Max Activating Token Index: 730

Text #17

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0631. Min Act: -0.0000

Data Index: 1953312 (The Pile)

Max Activating Token Index: 673

Text #18

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0582. Min Act: -0.0001

Data Index: 1919074 (The Pile)

Max Activating Token Index: 544

Text #19

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0558. Min Act: -0.0001

Data Index: 577267 (The Pile)

Max Activating Token Index: 311