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

Dataset: The Pile

Neuron 2600 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.9845. Min Range: -4.9845

Max Act: 4.8506. Min Act: -0.0000

Data Index: 660334 (The Pile)

Max Activating Token Index: 138

Text #1

Max Range: 4.9845. Min Range: -4.9845

Max Act: 4.9845. Min Act: -0.0000

Data Index: 1433247 (The Pile)

Max Activating Token Index: 914

Text #2

Max Range: 4.9845. Min Range: -4.9845

Max Act: 3.5367. Min Act: -0.0000

Data Index: 1513371 (The Pile)

Max Activating Token Index: 976

Text #3

Max Range: 4.9845. Min Range: -4.9845

Max Act: 4.5243. Min Act: -0.0000

Data Index: 124853 (The Pile)

Max Activating Token Index: 442

Text #4

Max Range: 4.9845. Min Range: -4.9845

Max Act: 4.1716. Min Act: -0.0000

Data Index: 1571859 (The Pile)

Max Activating Token Index: 508

Text #5

Max Range: 4.9845. Min Range: -4.9845

Max Act: 4.1100. Min Act: -0.0000

Data Index: 1558475 (The Pile)

Max Activating Token Index: 69

Text #6

Max Range: 4.9845. Min Range: -4.9845

Max Act: 3.8149. Min Act: -0.0000

Data Index: 836584 (The Pile)

Max Activating Token Index: 664

Text #7

Max Range: 4.9845. Min Range: -4.9845

Max Act: 3.7522. Min Act: -0.0000

Data Index: 463480 (The Pile)

Max Activating Token Index: 503

Text #8

Max Range: 4.9845. Min Range: -4.9845

Max Act: 4.0695. Min Act: -0.0000

Data Index: 503769 (The Pile)

Max Activating Token Index: 489

Text #9

Max Range: 4.9845. Min Range: -4.9845

Max Act: 3.9415. Min Act: -0.0000

Data Index: 1556395 (The Pile)

Max Activating Token Index: 630

Text #10

Max Range: 4.9845. Min Range: -4.9845

Max Act: 4.1335. Min Act: -0.0000

Data Index: 1991898 (The Pile)

Max Activating Token Index: 888

Text #11

Max Range: 4.9845. Min Range: -4.9845

Max Act: 3.7008. Min Act: -0.0000

Data Index: 1626440 (The Pile)

Max Activating Token Index: 309

Text #12

Max Range: 4.9845. Min Range: -4.9845

Max Act: 3.9923. Min Act: -0.0000

Data Index: 1334635 (The Pile)

Max Activating Token Index: 664

Text #13

Max Range: 4.9845. Min Range: -4.9845

Max Act: 3.3723. Min Act: -0.0000

Data Index: 642014 (The Pile)

Max Activating Token Index: 962

Text #14

Max Range: 4.9845. Min Range: -4.9845

Max Act: 3.4091. Min Act: -0.0000

Data Index: 1950484 (The Pile)

Max Activating Token Index: 96

Text #15

Max Range: 4.9845. Min Range: -4.9845

Max Act: 3.9738. Min Act: -0.0000

Data Index: 524631 (The Pile)

Max Activating Token Index: 414

Text #16

Max Range: 4.9845. Min Range: -4.9845

Max Act: 3.5756. Min Act: -0.0000

Data Index: 465244 (The Pile)

Max Activating Token Index: 426

Text #17

Max Range: 4.9845. Min Range: -4.9845

Max Act: 3.3221. Min Act: -0.0000

Data Index: 729771 (The Pile)

Max Activating Token Index: 508

Text #18

Max Range: 4.9845. Min Range: -4.9845

Max Act: 3.3205. Min Act: -0.0000

Data Index: 563081 (The Pile)

Max Activating Token Index: 333

Text #19

Max Range: 4.9845. Min Range: -4.9845

Max Act: 3.7760. Min Act: -0.0000

Data Index: 1103935 (The Pile)

Max Activating Token Index: 245