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

Dataset: The Pile

Neuron 3967 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: 2.1487. Min Range: -2.1487

Max Act: 2.1487. Min Act: -0.0000

Data Index: 1723073 (The Pile)

Max Activating Token Index: 822

Text #1

Max Range: 2.1487. Min Range: -2.1487

Max Act: 1.7628. Min Act: -0.0000

Data Index: 388921 (The Pile)

Max Activating Token Index: 1008

Text #2

Max Range: 2.1487. Min Range: -2.1487

Max Act: 1.5856. Min Act: -0.0000

Data Index: 1215137 (The Pile)

Max Activating Token Index: 788

Text #3

Max Range: 2.1487. Min Range: -2.1487

Max Act: 1.6931. Min Act: -0.0000

Data Index: 1878074 (The Pile)

Max Activating Token Index: 596

Text #4

Max Range: 2.1487. Min Range: -2.1487

Max Act: 1.4731. Min Act: -0.0000

Data Index: 125700 (The Pile)

Max Activating Token Index: 745

Text #5

Max Range: 2.1487. Min Range: -2.1487

Max Act: 1.6723. Min Act: -0.0000

Data Index: 496376 (The Pile)

Max Activating Token Index: 624

Text #6

Max Range: 2.1487. Min Range: -2.1487

Max Act: 1.3469. Min Act: -0.0000

Data Index: 477074 (The Pile)

Max Activating Token Index: 647

Text #7

Max Range: 2.1487. Min Range: -2.1487

Max Act: 1.4409. Min Act: -0.0000

Data Index: 467412 (The Pile)

Max Activating Token Index: 980

Text #8

Max Range: 2.1487. Min Range: -2.1487

Max Act: 1.3097. Min Act: -0.0000

Data Index: 1999069 (The Pile)

Max Activating Token Index: 572

Text #9

Max Range: 2.1487. Min Range: -2.1487

Max Act: 1.4538. Min Act: -0.0000

Data Index: 281495 (The Pile)

Max Activating Token Index: 366

Text #10

Max Range: 2.1487. Min Range: -2.1487

Max Act: 1.3524. Min Act: -0.0000

Data Index: 1277985 (The Pile)

Max Activating Token Index: 539

Text #11

Max Range: 2.1487. Min Range: -2.1487

Max Act: 1.3374. Min Act: -0.0000

Data Index: 627838 (The Pile)

Max Activating Token Index: 192

Text #12

Max Range: 2.1487. Min Range: -2.1487

Max Act: 1.2523. Min Act: -0.0000

Data Index: 1688434 (The Pile)

Max Activating Token Index: 766

Text #13

Max Range: 2.1487. Min Range: -2.1487

Max Act: 1.3037. Min Act: -0.0000

Data Index: 1806484 (The Pile)

Max Activating Token Index: 428

Text #14

Max Range: 2.1487. Min Range: -2.1487

Max Act: 1.1892. Min Act: -0.0000

Data Index: 986557 (The Pile)

Max Activating Token Index: 359

Text #15

Max Range: 2.1487. Min Range: -2.1487

Max Act: 1.3609. Min Act: -0.0000

Data Index: 734245 (The Pile)

Max Activating Token Index: 258

Text #16

Max Range: 2.1487. Min Range: -2.1487

Max Act: 1.2606. Min Act: -0.0000

Data Index: 1212544 (The Pile)

Max Activating Token Index: 802

Text #17

Max Range: 2.1487. Min Range: -2.1487

Max Act: 1.2557. Min Act: -0.0000

Data Index: 605730 (The Pile)

Max Activating Token Index: 607

Text #18

Max Range: 2.1487. Min Range: -2.1487

Max Act: 1.2288. Min Act: -0.0000

Data Index: 1757324 (The Pile)

Max Activating Token Index: 551

Text #19

Max Range: 2.1487. Min Range: -2.1487

Max Act: 1.2344. Min Act: -0.0000

Data Index: 855177 (The Pile)

Max Activating Token Index: 404