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

Dataset: The Pile

Neuron 1025 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: 0.6847. Min Range: -0.6847

Max Act: 0.6847. Min Act: -0.0000

Data Index: 1621619 (The Pile)

Max Activating Token Index: 581

Text #1

Max Range: 0.6847. Min Range: -0.6847

Max Act: 0.6078. Min Act: -0.0000

Data Index: 551086 (The Pile)

Max Activating Token Index: 636

Text #2

Max Range: 0.6847. Min Range: -0.6847

Max Act: 0.6431. Min Act: -0.0000

Data Index: 1575506 (The Pile)

Max Activating Token Index: 418

Text #3

Max Range: 0.6847. Min Range: -0.6847

Max Act: 0.5863. Min Act: -0.0000

Data Index: 1715570 (The Pile)

Max Activating Token Index: 919

Text #4

Max Range: 0.6847. Min Range: -0.6847

Max Act: 0.5726. Min Act: -0.0000

Data Index: 181643 (The Pile)

Max Activating Token Index: 912

Text #5

Max Range: 0.6847. Min Range: -0.6847

Max Act: 0.5354. Min Act: -0.0000

Data Index: 658327 (The Pile)

Max Activating Token Index: 659

Text #6

Max Range: 0.6847. Min Range: -0.6847

Max Act: 0.5359. Min Act: -0.0000

Data Index: 1402675 (The Pile)

Max Activating Token Index: 291

Text #7

Max Range: 0.6847. Min Range: -0.6847

Max Act: 0.5702. Min Act: -0.0000

Data Index: 722668 (The Pile)

Max Activating Token Index: 810

Text #8

Max Range: 0.6847. Min Range: -0.6847

Max Act: 0.5332. Min Act: -0.0000

Data Index: 1433374 (The Pile)

Max Activating Token Index: 254

Text #9

Max Range: 0.6847. Min Range: -0.6847

Max Act: 0.5251. Min Act: -0.0000

Data Index: 39875 (The Pile)

Max Activating Token Index: 337

Text #10

Max Range: 0.6847. Min Range: -0.6847

Max Act: 0.4908. Min Act: -0.0000

Data Index: 304915 (The Pile)

Max Activating Token Index: 847

Text #11

Max Range: 0.6847. Min Range: -0.6847

Max Act: 0.5092. Min Act: -0.0000

Data Index: 332854 (The Pile)

Max Activating Token Index: 594

Text #12

Max Range: 0.6847. Min Range: -0.6847

Max Act: 0.4905. Min Act: -0.0000

Data Index: 1186445 (The Pile)

Max Activating Token Index: 904

Text #13

Max Range: 0.6847. Min Range: -0.6847

Max Act: 0.4817. Min Act: -0.0000

Data Index: 1703000 (The Pile)

Max Activating Token Index: 496

Text #14

Max Range: 0.6847. Min Range: -0.6847

Max Act: 0.4769. Min Act: -0.0000

Data Index: 1970689 (The Pile)

Max Activating Token Index: 90

Text #15

Max Range: 0.6847. Min Range: -0.6847

Max Act: 0.4634. Min Act: -0.0000

Data Index: 1834229 (The Pile)

Max Activating Token Index: 781

Text #16

Max Range: 0.6847. Min Range: -0.6847

Max Act: 0.4900. Min Act: -0.0000

Data Index: 700268 (The Pile)

Max Activating Token Index: 953

Text #17

Max Range: 0.6847. Min Range: -0.6847

Max Act: 0.4585. Min Act: -0.0000

Data Index: 236068 (The Pile)

Max Activating Token Index: 431

Text #18

Max Range: 0.6847. Min Range: -0.6847

Max Act: 0.4385. Min Act: -0.0000

Data Index: 120045 (The Pile)

Max Activating Token Index: 540

Text #19

Max Range: 0.6847. Min Range: -0.6847

Max Act: 0.4748. Min Act: -0.0000

Data Index: 1260040 (The Pile)

Max Activating Token Index: 609