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

Dataset: The Pile

Neuron 3483 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: 0.0698. Min Range: -0.0698

Max Act: 0.0698. Min Act: -0.0000

Data Index: 430513 (The Pile)

Max Activating Token Index: 522

Text #1

Max Range: 0.0698. Min Range: -0.0698

Max Act: 0.0641. Min Act: -0.0000

Data Index: 616652 (The Pile)

Max Activating Token Index: 993

Text #2

Max Range: 0.0698. Min Range: -0.0698

Max Act: 0.0546. Min Act: -0.0000

Data Index: 731183 (The Pile)

Max Activating Token Index: 309

Text #3

Max Range: 0.0698. Min Range: -0.0698

Max Act: 0.0611. Min Act: -0.0000

Data Index: 1152971 (The Pile)

Max Activating Token Index: 636

Text #4

Max Range: 0.0698. Min Range: -0.0698

Max Act: 0.0563. Min Act: -0.0000

Data Index: 271006 (The Pile)

Max Activating Token Index: 470

Text #5

Max Range: 0.0698. Min Range: -0.0698

Max Act: 0.0560. Min Act: -0.0000

Data Index: 1921568 (The Pile)

Max Activating Token Index: 457

Text #6

Max Range: 0.0698. Min Range: -0.0698

Max Act: 0.0548. Min Act: -0.0000

Data Index: 1559058 (The Pile)

Max Activating Token Index: 462

Text #7

Max Range: 0.0698. Min Range: -0.0698

Max Act: 0.0534. Min Act: -0.0000

Data Index: 1662054 (The Pile)

Max Activating Token Index: 46

Text #8

Max Range: 0.0698. Min Range: -0.0698

Max Act: 0.0490. Min Act: -0.0000

Data Index: 448591 (The Pile)

Max Activating Token Index: 230

Text #9

Max Range: 0.0698. Min Range: -0.0698

Max Act: 0.0485. Min Act: -0.0000

Data Index: 1033856 (The Pile)

Max Activating Token Index: 69

Text #10

Max Range: 0.0698. Min Range: -0.0698

Max Act: 0.0499. Min Act: -0.0000

Data Index: 1707977 (The Pile)

Max Activating Token Index: 384

Text #11

Max Range: 0.0698. Min Range: -0.0698

Max Act: 0.0466. Min Act: -0.0000

Data Index: 911117 (The Pile)

Max Activating Token Index: 50

Text #12

Max Range: 0.0698. Min Range: -0.0698

Max Act: 0.0482. Min Act: -0.0000

Data Index: 1042864 (The Pile)

Max Activating Token Index: 456

Text #13

Max Range: 0.0698. Min Range: -0.0698

Max Act: 0.0477. Min Act: -0.0000

Data Index: 1789106 (The Pile)

Max Activating Token Index: 480

Text #14

Max Range: 0.0698. Min Range: -0.0698

Max Act: 0.0472. Min Act: -0.0000

Data Index: 667405 (The Pile)

Max Activating Token Index: 641

Text #15

Max Range: 0.0698. Min Range: -0.0698

Max Act: 0.0451. Min Act: -0.0000

Data Index: 1912172 (The Pile)

Max Activating Token Index: 354

Text #16

Max Range: 0.0698. Min Range: -0.0698

Max Act: 0.0468. Min Act: -0.0000

Data Index: 639992 (The Pile)

Max Activating Token Index: 700

Text #17

Max Range: 0.0698. Min Range: -0.0698

Max Act: 0.0460. Min Act: -0.0000

Data Index: 1364577 (The Pile)

Max Activating Token Index: 651

Text #18

Max Range: 0.0698. Min Range: -0.0698

Max Act: 0.0457. Min Act: -0.0000

Data Index: 865076 (The Pile)

Max Activating Token Index: 681

Text #19

Max Range: 0.0698. Min Range: -0.0698

Max Act: 0.0490. Min Act: -0.0000

Data Index: 452685 (The Pile)

Max Activating Token Index: 418