Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 609 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.5838. Min Range: -0.5838

Max Act: 0.5838. Min Act: -0.0000

Data Index: 1990694 (The Pile)

Max Activating Token Index: 500

Text #1

Max Range: 0.5838. Min Range: -0.5838

Max Act: 0.5090. Min Act: -0.0000

Data Index: 866378 (The Pile)

Max Activating Token Index: 352

Text #2

Max Range: 0.5838. Min Range: -0.5838

Max Act: 0.4484. Min Act: -0.0000

Data Index: 856155 (The Pile)

Max Activating Token Index: 631

Text #3

Max Range: 0.5838. Min Range: -0.5838

Max Act: 0.4577. Min Act: -0.0000

Data Index: 1737413 (The Pile)

Max Activating Token Index: 828

Text #4

Max Range: 0.5838. Min Range: -0.5838

Max Act: 0.4429. Min Act: -0.0000

Data Index: 1477397 (The Pile)

Max Activating Token Index: 472

Text #5

Max Range: 0.5838. Min Range: -0.5838

Max Act: 0.4234. Min Act: -0.0000

Data Index: 1180930 (The Pile)

Max Activating Token Index: 1020

Text #6

Max Range: 0.5838. Min Range: -0.5838

Max Act: 0.4443. Min Act: -0.0000

Data Index: 1925228 (The Pile)

Max Activating Token Index: 316

Text #7

Max Range: 0.5838. Min Range: -0.5838

Max Act: 0.4201. Min Act: -0.0000

Data Index: 353969 (The Pile)

Max Activating Token Index: 451

Text #8

Max Range: 0.5838. Min Range: -0.5838

Max Act: 0.4188. Min Act: -0.0000

Data Index: 596328 (The Pile)

Max Activating Token Index: 592

Text #9

Max Range: 0.5838. Min Range: -0.5838

Max Act: 0.3926. Min Act: -0.0000

Data Index: 703937 (The Pile)

Max Activating Token Index: 476

Text #10

Max Range: 0.5838. Min Range: -0.5838

Max Act: 0.3910. Min Act: -0.0000

Data Index: 842369 (The Pile)

Max Activating Token Index: 595

Text #11

Max Range: 0.5838. Min Range: -0.5838

Max Act: 0.4010. Min Act: -0.0000

Data Index: 63431 (The Pile)

Max Activating Token Index: 780

Text #12

Max Range: 0.5838. Min Range: -0.5838

Max Act: 0.3911. Min Act: -0.0000

Data Index: 836003 (The Pile)

Max Activating Token Index: 225

Text #13

Max Range: 0.5838. Min Range: -0.5838

Max Act: 0.3762. Min Act: -0.0000

Data Index: 895129 (The Pile)

Max Activating Token Index: 266

Text #14

Max Range: 0.5838. Min Range: -0.5838

Max Act: 0.3775. Min Act: -0.0000

Data Index: 356145 (The Pile)

Max Activating Token Index: 800

Text #15

Max Range: 0.5838. Min Range: -0.5838

Max Act: 0.3824. Min Act: -0.0000

Data Index: 1396910 (The Pile)

Max Activating Token Index: 942

Text #16

Max Range: 0.5838. Min Range: -0.5838

Max Act: 0.3818. Min Act: -0.0000

Data Index: 101199 (The Pile)

Max Activating Token Index: 948

Text #17

Max Range: 0.5838. Min Range: -0.5838

Max Act: 0.3567. Min Act: -0.0000

Data Index: 950180 (The Pile)

Max Activating Token Index: 566

Text #18

Max Range: 0.5838. Min Range: -0.5838

Max Act: 0.3759. Min Act: -0.0000

Data Index: 375729 (The Pile)

Max Activating Token Index: 186

Text #19

Max Range: 0.5838. Min Range: -0.5838

Max Act: 0.3890. Min Act: -0.0000

Data Index: 397885 (The Pile)

Max Activating Token Index: 289