Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

Dataset: The Pile

Neuron 2432 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l-pile')

Text #0

Max Range: 0.3663. Min Range: -0.3663

Max Act: 0.3594. Min Act: -0.0000

Data Index: 49494 (The Pile)

Max Activating Token Index: 1011

Text #1

Max Range: 0.3663. Min Range: -0.3663

Max Act: 0.3663. Min Act: -0.0000

Data Index: 1747072 (The Pile)

Max Activating Token Index: 259

Text #2

Max Range: 0.3663. Min Range: -0.3663

Max Act: 0.3551. Min Act: -0.0001

Data Index: 1718528 (The Pile)

Max Activating Token Index: 922

Text #3

Max Range: 0.3663. Min Range: -0.3663

Max Act: 0.3508. Min Act: -0.0000

Data Index: 758466 (The Pile)

Max Activating Token Index: 232

Text #4

Max Range: 0.3663. Min Range: -0.3663

Max Act: 0.3624. Min Act: -0.0000

Data Index: 776616 (The Pile)

Max Activating Token Index: 435

Text #5

Max Range: 0.3663. Min Range: -0.3663

Max Act: 0.3499. Min Act: -0.0000

Data Index: 304448 (The Pile)

Max Activating Token Index: 702

Text #6

Max Range: 0.3663. Min Range: -0.3663

Max Act: 0.3472. Min Act: -0.0000

Data Index: 575848 (The Pile)

Max Activating Token Index: 674

Text #7

Max Range: 0.3663. Min Range: -0.3663

Max Act: 0.3482. Min Act: -0.0000

Data Index: 213993 (The Pile)

Max Activating Token Index: 631

Text #8

Max Range: 0.3663. Min Range: -0.3663

Max Act: 0.3377. Min Act: -0.0000

Data Index: 1567715 (The Pile)

Max Activating Token Index: 575

Text #9

Max Range: 0.3663. Min Range: -0.3663

Max Act: 0.3445. Min Act: -0.0000

Data Index: 1407358 (The Pile)

Max Activating Token Index: 880

Text #10

Max Range: 0.3663. Min Range: -0.3663

Max Act: 0.3331. Min Act: -0.0000

Data Index: 1087179 (The Pile)

Max Activating Token Index: 982

Text #11

Max Range: 0.3663. Min Range: -0.3663

Max Act: 0.3379. Min Act: -0.0000

Data Index: 804252 (The Pile)

Max Activating Token Index: 765

Text #12

Max Range: 0.3663. Min Range: -0.3663

Max Act: 0.3352. Min Act: -0.0000

Data Index: 1251743 (The Pile)

Max Activating Token Index: 372

Text #13

Max Range: 0.3663. Min Range: -0.3663

Max Act: 0.3344. Min Act: -0.0000

Data Index: 1557034 (The Pile)

Max Activating Token Index: 431

Text #14

Max Range: 0.3663. Min Range: -0.3663

Max Act: 0.3446. Min Act: -0.0000

Data Index: 795369 (The Pile)

Max Activating Token Index: 446

Text #15

Max Range: 0.3663. Min Range: -0.3663

Max Act: 0.3220. Min Act: -0.0000

Data Index: 36747 (The Pile)

Max Activating Token Index: 870

Text #16

Max Range: 0.3663. Min Range: -0.3663

Max Act: 0.3326. Min Act: -0.0000

Data Index: 110563 (The Pile)

Max Activating Token Index: 706

Text #17

Max Range: 0.3663. Min Range: -0.3663

Max Act: 0.3444. Min Act: -0.0000

Data Index: 787482 (The Pile)

Max Activating Token Index: 206

Text #18

Max Range: 0.3663. Min Range: -0.3663

Max Act: 0.3314. Min Act: -0.0000

Data Index: 1300639 (The Pile)

Max Activating Token Index: 938

Text #19

Max Range: 0.3663. Min Range: -0.3663

Max Act: 0.3306. Min Act: -0.0000

Data Index: 951494 (The Pile)

Max Activating Token Index: 888