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

Dataset: The Pile

Neuron 613 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6467. Min Range: -1.6467

Max Act: 1.6467. Min Act: -0.0000

Data Index: 817386 (The Pile)

Max Activating Token Index: 929

Text #1

Max Range: 1.6467. Min Range: -1.6467

Max Act: 1.4585. Min Act: -0.0000

Data Index: 1046942 (The Pile)

Max Activating Token Index: 488

Text #2

Max Range: 1.6467. Min Range: -1.6467

Max Act: 1.4189. Min Act: -0.0000

Data Index: 926214 (The Pile)

Max Activating Token Index: 1012

Text #3

Max Range: 1.6467. Min Range: -1.6467

Max Act: 1.4702. Min Act: -0.0000

Data Index: 1087954 (The Pile)

Max Activating Token Index: 407

Text #4

Max Range: 1.6467. Min Range: -1.6467

Max Act: 1.3844. Min Act: -0.0000

Data Index: 858699 (The Pile)

Max Activating Token Index: 278

Text #5

Max Range: 1.6467. Min Range: -1.6467

Max Act: 1.3758. Min Act: -0.0000

Data Index: 994938 (The Pile)

Max Activating Token Index: 707

Text #6

Max Range: 1.6467. Min Range: -1.6467

Max Act: 1.5367. Min Act: -0.0000

Data Index: 1406776 (The Pile)

Max Activating Token Index: 546

Text #7

Max Range: 1.6467. Min Range: -1.6467

Max Act: 1.3840. Min Act: -0.0000

Data Index: 1998159 (The Pile)

Max Activating Token Index: 339

Text #8

Max Range: 1.6467. Min Range: -1.6467

Max Act: 1.3747. Min Act: -0.0000

Data Index: 870283 (The Pile)

Max Activating Token Index: 526

Text #9

Max Range: 1.6467. Min Range: -1.6467

Max Act: 1.3623. Min Act: -0.0000

Data Index: 814002 (The Pile)

Max Activating Token Index: 1004

Text #10

Max Range: 1.6467. Min Range: -1.6467

Max Act: 1.3668. Min Act: -0.0000

Data Index: 1935726 (The Pile)

Max Activating Token Index: 779

Text #11

Max Range: 1.6467. Min Range: -1.6467

Max Act: 1.4351. Min Act: -0.0000

Data Index: 1222975 (The Pile)

Max Activating Token Index: 499

Text #12

Max Range: 1.6467. Min Range: -1.6467

Max Act: 1.5056. Min Act: -0.0000

Data Index: 1407886 (The Pile)

Max Activating Token Index: 1006

Text #13

Max Range: 1.6467. Min Range: -1.6467

Max Act: 1.3410. Min Act: -0.0000

Data Index: 738719 (The Pile)

Max Activating Token Index: 532

Text #14

Max Range: 1.6467. Min Range: -1.6467

Max Act: 1.3680. Min Act: -0.0000

Data Index: 1221687 (The Pile)

Max Activating Token Index: 847

Text #15

Max Range: 1.6467. Min Range: -1.6467

Max Act: 1.3228. Min Act: -0.0000

Data Index: 771600 (The Pile)

Max Activating Token Index: 319

Text #16

Max Range: 1.6467. Min Range: -1.6467

Max Act: 1.3715. Min Act: -0.0000

Data Index: 1378884 (The Pile)

Max Activating Token Index: 919

Text #17

Max Range: 1.6467. Min Range: -1.6467

Max Act: 1.5002. Min Act: -0.0000

Data Index: 386048 (The Pile)

Max Activating Token Index: 997

Text #18

Max Range: 1.6467. Min Range: -1.6467

Max Act: 1.4016. Min Act: -0.0000

Data Index: 1413805 (The Pile)

Max Activating Token Index: 198

Text #19

Max Range: 1.6467. Min Range: -1.6467

Max Act: 1.3192. Min Act: -0.0000

Data Index: 1879482 (The Pile)

Max Activating Token Index: 254