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

Dataset: The Pile

Neuron 1457 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: 8.5649. Min Range: -8.5649

Max Act: 8.5649. Min Act: -0.0000

Data Index: 1951312 (The Pile)

Max Activating Token Index: 726

Text #1

Max Range: 8.5649. Min Range: -8.5649

Max Act: 8.2777. Min Act: -0.0000

Data Index: 1234857 (The Pile)

Max Activating Token Index: 324

Text #2

Max Range: 8.5649. Min Range: -8.5649

Max Act: 8.2060. Min Act: -0.0000

Data Index: 1039622 (The Pile)

Max Activating Token Index: 57

Text #3

Max Range: 8.5649. Min Range: -8.5649

Max Act: 7.9358. Min Act: -0.0000

Data Index: 293842 (The Pile)

Max Activating Token Index: 571

Text #4

Max Range: 8.5649. Min Range: -8.5649

Max Act: 7.9290. Min Act: -0.0000

Data Index: 535651 (The Pile)

Max Activating Token Index: 399

Text #5

Max Range: 8.5649. Min Range: -8.5649

Max Act: 8.0400. Min Act: -0.0000

Data Index: 1069308 (The Pile)

Max Activating Token Index: 395

Text #6

Max Range: 8.5649. Min Range: -8.5649

Max Act: 7.5392. Min Act: -0.0000

Data Index: 397166 (The Pile)

Max Activating Token Index: 236

Text #7

Max Range: 8.5649. Min Range: -8.5649

Max Act: 7.8916. Min Act: -0.0000

Data Index: 1723520 (The Pile)

Max Activating Token Index: 90

Text #8

Max Range: 8.5649. Min Range: -8.5649

Max Act: 7.6283. Min Act: -0.0000

Data Index: 1623602 (The Pile)

Max Activating Token Index: 747

Text #9

Max Range: 8.5649. Min Range: -8.5649

Max Act: 7.5483. Min Act: -0.0000

Data Index: 285430 (The Pile)

Max Activating Token Index: 464

Text #10

Max Range: 8.5649. Min Range: -8.5649

Max Act: 7.4796. Min Act: 0.0000

Data Index: 20403 (The Pile)

Max Activating Token Index: 144

Text #11

Max Range: 8.5649. Min Range: -8.5649

Max Act: 7.0264. Min Act: -0.0000

Data Index: 801887 (The Pile)

Max Activating Token Index: 51

Text #12

Max Range: 8.5649. Min Range: -8.5649

Max Act: 7.1737. Min Act: -0.0000

Data Index: 1972967 (The Pile)

Max Activating Token Index: 581

Text #13

Max Range: 8.5649. Min Range: -8.5649

Max Act: 7.3386. Min Act: -0.0000

Data Index: 1537741 (The Pile)

Max Activating Token Index: 614

Text #14

Max Range: 8.5649. Min Range: -8.5649

Max Act: 7.1598. Min Act: -0.0000

Data Index: 895573 (The Pile)

Max Activating Token Index: 289

Text #15

Max Range: 8.5649. Min Range: -8.5649

Max Act: 7.1178. Min Act: -0.0000

Data Index: 145102 (The Pile)

Max Activating Token Index: 514

Text #16

Max Range: 8.5649. Min Range: -8.5649

Max Act: 6.8397. Min Act: -0.0000

Data Index: 1077661 (The Pile)

Max Activating Token Index: 245

Text #17

Max Range: 8.5649. Min Range: -8.5649

Max Act: 7.0134. Min Act: 0.0000

Data Index: 1947418 (The Pile)

Max Activating Token Index: 923

Text #18

Max Range: 8.5649. Min Range: -8.5649

Max Act: 7.0153. Min Act: -0.0000

Data Index: 759061 (The Pile)

Max Activating Token Index: 35

Text #19

Max Range: 8.5649. Min Range: -8.5649

Max Act: 7.1334. Min Act: -0.0000

Data Index: 1282021 (The Pile)

Max Activating Token Index: 585