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

Dataset: The Pile

Neuron 1036 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4357. Min Range: -0.4357

Max Act: 0.4228. Min Act: -0.0000

Data Index: 1938335 (The Pile)

Max Activating Token Index: 738

Text #1

Max Range: 0.4357. Min Range: -0.4357

Max Act: 0.4032. Min Act: -0.0000

Data Index: 202877 (The Pile)

Max Activating Token Index: 688

Text #2

Max Range: 0.4357. Min Range: -0.4357

Max Act: 0.3867. Min Act: -0.0000

Data Index: 817941 (The Pile)

Max Activating Token Index: 553

Text #3

Max Range: 0.4357. Min Range: -0.4357

Max Act: 0.4357. Min Act: -0.0000

Data Index: 646047 (The Pile)

Max Activating Token Index: 958

Text #4

Max Range: 0.4357. Min Range: -0.4357

Max Act: 0.3938. Min Act: -0.0000

Data Index: 13719 (The Pile)

Max Activating Token Index: 479

Text #5

Max Range: 0.4357. Min Range: -0.4357

Max Act: 0.3844. Min Act: -0.0000

Data Index: 517170 (The Pile)

Max Activating Token Index: 940

Text #6

Max Range: 0.4357. Min Range: -0.4357

Max Act: 0.3457. Min Act: -0.0000

Data Index: 457489 (The Pile)

Max Activating Token Index: 454

Text #7

Max Range: 0.4357. Min Range: -0.4357

Max Act: 0.3858. Min Act: -0.0000

Data Index: 713337 (The Pile)

Max Activating Token Index: 495

Text #8

Max Range: 0.4357. Min Range: -0.4357

Max Act: 0.4055. Min Act: -0.0000

Data Index: 626132 (The Pile)

Max Activating Token Index: 332

Text #9

Max Range: 0.4357. Min Range: -0.4357

Max Act: 0.3600. Min Act: -0.0000

Data Index: 367875 (The Pile)

Max Activating Token Index: 574

Text #10

Max Range: 0.4357. Min Range: -0.4357

Max Act: 0.3507. Min Act: -0.0000

Data Index: 532810 (The Pile)

Max Activating Token Index: 994

Text #11

Max Range: 0.4357. Min Range: -0.4357

Max Act: 0.3294. Min Act: -0.0000

Data Index: 1371698 (The Pile)

Max Activating Token Index: 770

Text #12

Max Range: 0.4357. Min Range: -0.4357

Max Act: 0.3604. Min Act: -0.0000

Data Index: 1314822 (The Pile)

Max Activating Token Index: 557

Text #13

Max Range: 0.4357. Min Range: -0.4357

Max Act: 0.3488. Min Act: -0.0000

Data Index: 1809259 (The Pile)

Max Activating Token Index: 609

Text #14

Max Range: 0.4357. Min Range: -0.4357

Max Act: 0.3398. Min Act: -0.0000

Data Index: 749521 (The Pile)

Max Activating Token Index: 676

Text #15

Max Range: 0.4357. Min Range: -0.4357

Max Act: 0.3592. Min Act: -0.0000

Data Index: 1528430 (The Pile)

Max Activating Token Index: 766

Text #16

Max Range: 0.4357. Min Range: -0.4357

Max Act: 0.3407. Min Act: -0.0000

Data Index: 1692103 (The Pile)

Max Activating Token Index: 726

Text #17

Max Range: 0.4357. Min Range: -0.4357

Max Act: 0.3230. Min Act: -0.0000

Data Index: 561479 (The Pile)

Max Activating Token Index: 469

Text #18

Max Range: 0.4357. Min Range: -0.4357

Max Act: 0.3504. Min Act: -0.0000

Data Index: 1766333 (The Pile)

Max Activating Token Index: 207

Text #19

Max Range: 0.4357. Min Range: -0.4357

Max Act: 0.3795. Min Act: -0.0000

Data Index: 380157 (The Pile)

Max Activating Token Index: 739