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

Dataset: The Pile

Neuron 2486 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5507. Min Range: -0.5507

Max Act: 0.5507. Min Act: -0.0000

Data Index: 431391 (The Pile)

Max Activating Token Index: 170

Text #1

Max Range: 0.5507. Min Range: -0.5507

Max Act: 0.4588. Min Act: -0.0000

Data Index: 317487 (The Pile)

Max Activating Token Index: 938

Text #2

Max Range: 0.5507. Min Range: -0.5507

Max Act: 0.4479. Min Act: -0.0000

Data Index: 1948332 (The Pile)

Max Activating Token Index: 766

Text #3

Max Range: 0.5507. Min Range: -0.5507

Max Act: 0.4357. Min Act: -0.0000

Data Index: 894621 (The Pile)

Max Activating Token Index: 744

Text #4

Max Range: 0.5507. Min Range: -0.5507

Max Act: 0.4263. Min Act: -0.0000

Data Index: 1966986 (The Pile)

Max Activating Token Index: 464

Text #5

Max Range: 0.5507. Min Range: -0.5507

Max Act: 0.3881. Min Act: -0.0000

Data Index: 324803 (The Pile)

Max Activating Token Index: 906

Text #6

Max Range: 0.5507. Min Range: -0.5507

Max Act: 0.4126. Min Act: -0.0000

Data Index: 477478 (The Pile)

Max Activating Token Index: 674

Text #7

Max Range: 0.5507. Min Range: -0.5507

Max Act: 0.3570. Min Act: -0.0000

Data Index: 1674304 (The Pile)

Max Activating Token Index: 861

Text #8

Max Range: 0.5507. Min Range: -0.5507

Max Act: 0.3534. Min Act: -0.0000

Data Index: 630942 (The Pile)

Max Activating Token Index: 895

Text #9

Max Range: 0.5507. Min Range: -0.5507

Max Act: 0.4182. Min Act: -0.0000

Data Index: 864848 (The Pile)

Max Activating Token Index: 656

Text #10

Max Range: 0.5507. Min Range: -0.5507

Max Act: 0.3795. Min Act: -0.0000

Data Index: 976979 (The Pile)

Max Activating Token Index: 342

Text #11

Max Range: 0.5507. Min Range: -0.5507

Max Act: 0.3847. Min Act: -0.0000

Data Index: 995734 (The Pile)

Max Activating Token Index: 653

Text #12

Max Range: 0.5507. Min Range: -0.5507

Max Act: 0.3669. Min Act: -0.0000

Data Index: 1684430 (The Pile)

Max Activating Token Index: 322

Text #13

Max Range: 0.5507. Min Range: -0.5507

Max Act: 0.3827. Min Act: -0.0000

Data Index: 1773625 (The Pile)

Max Activating Token Index: 731

Text #14

Max Range: 0.5507. Min Range: -0.5507

Max Act: 0.3456. Min Act: -0.0000

Data Index: 1132017 (The Pile)

Max Activating Token Index: 264

Text #15

Max Range: 0.5507. Min Range: -0.5507

Max Act: 0.3855. Min Act: -0.0000

Data Index: 1458112 (The Pile)

Max Activating Token Index: 380

Text #16

Max Range: 0.5507. Min Range: -0.5507

Max Act: 0.3506. Min Act: -0.0000

Data Index: 899403 (The Pile)

Max Activating Token Index: 860

Text #17

Max Range: 0.5507. Min Range: -0.5507

Max Act: 0.3344. Min Act: -0.0000

Data Index: 249717 (The Pile)

Max Activating Token Index: 248

Text #18

Max Range: 0.5507. Min Range: -0.5507

Max Act: 0.3907. Min Act: -0.0000

Data Index: 50526 (The Pile)

Max Activating Token Index: 588

Text #19

Max Range: 0.5507. Min Range: -0.5507

Max Act: 0.3631. Min Act: -0.0000

Data Index: 1128301 (The Pile)

Max Activating Token Index: 1018