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

Dataset: The Pile

Neuron 4122 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: 1.4563. Min Range: -1.4563

Max Act: 1.4563. Min Act: -0.0000

Data Index: 20323 (The Pile)

Max Activating Token Index: 177

Text #1

Max Range: 1.4563. Min Range: -1.4563

Max Act: 1.3430. Min Act: -0.0000

Data Index: 722387 (The Pile)

Max Activating Token Index: 341

Text #2

Max Range: 1.4563. Min Range: -1.4563

Max Act: 1.3918. Min Act: -0.0000

Data Index: 356355 (The Pile)

Max Activating Token Index: 789

Text #3

Max Range: 1.4563. Min Range: -1.4563

Max Act: 1.3506. Min Act: -0.0000

Data Index: 1580730 (The Pile)

Max Activating Token Index: 95

Text #4

Max Range: 1.4563. Min Range: -1.4563

Max Act: 1.3310. Min Act: -0.0000

Data Index: 1022314 (The Pile)

Max Activating Token Index: 430

Text #5

Max Range: 1.4563. Min Range: -1.4563

Max Act: 1.3279. Min Act: -0.0000

Data Index: 256030 (The Pile)

Max Activating Token Index: 18

Text #6

Max Range: 1.4563. Min Range: -1.4563

Max Act: 1.2511. Min Act: -0.0000

Data Index: 1754447 (The Pile)

Max Activating Token Index: 751

Text #7

Max Range: 1.4563. Min Range: -1.4563

Max Act: 1.1277. Min Act: -0.0000

Data Index: 913668 (The Pile)

Max Activating Token Index: 177

Text #8

Max Range: 1.4563. Min Range: -1.4563

Max Act: 1.2042. Min Act: -0.0000

Data Index: 212924 (The Pile)

Max Activating Token Index: 374

Text #9

Max Range: 1.4563. Min Range: -1.4563

Max Act: 1.0360. Min Act: -0.0000

Data Index: 1242462 (The Pile)

Max Activating Token Index: 962

Text #10

Max Range: 1.4563. Min Range: -1.4563

Max Act: 1.1903. Min Act: -0.0000

Data Index: 1785022 (The Pile)

Max Activating Token Index: 873

Text #11

Max Range: 1.4563. Min Range: -1.4563

Max Act: 1.1528. Min Act: -0.0000

Data Index: 1269183 (The Pile)

Max Activating Token Index: 996

Text #12

Max Range: 1.4563. Min Range: -1.4563

Max Act: 1.1402. Min Act: -0.0000

Data Index: 32263 (The Pile)

Max Activating Token Index: 816

Text #13

Max Range: 1.4563. Min Range: -1.4563

Max Act: 1.0280. Min Act: -0.0000

Data Index: 1222970 (The Pile)

Max Activating Token Index: 147

Text #14

Max Range: 1.4563. Min Range: -1.4563

Max Act: 1.0513. Min Act: -0.0000

Data Index: 1940580 (The Pile)

Max Activating Token Index: 568

Text #15

Max Range: 1.4563. Min Range: -1.4563

Max Act: 0.9860. Min Act: -0.0000

Data Index: 1994818 (The Pile)

Max Activating Token Index: 950

Text #16

Max Range: 1.4563. Min Range: -1.4563

Max Act: 0.9446. Min Act: -0.0000

Data Index: 1421844 (The Pile)

Max Activating Token Index: 336

Text #17

Max Range: 1.4563. Min Range: -1.4563

Max Act: 0.9835. Min Act: -0.0000

Data Index: 410527 (The Pile)

Max Activating Token Index: 383

Text #18

Max Range: 1.4563. Min Range: -1.4563

Max Act: 0.9182. Min Act: -0.0000

Data Index: 1326554 (The Pile)

Max Activating Token Index: 613

Text #19

Max Range: 1.4563. Min Range: -1.4563

Max Act: 0.9327. Min Act: -0.0000

Data Index: 1834040 (The Pile)

Max Activating Token Index: 433