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

Dataset: The Pile

Neuron 3708 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1917. Min Range: -0.1917

Max Act: 0.1903. Min Act: -0.0000

Data Index: 1784720 (The Pile)

Max Activating Token Index: 284

Text #1

Max Range: 0.1917. Min Range: -0.1917

Max Act: 0.1814. Min Act: -0.0000

Data Index: 396321 (The Pile)

Max Activating Token Index: 431

Text #2

Max Range: 0.1917. Min Range: -0.1917

Max Act: 0.1903. Min Act: -0.0000

Data Index: 310700 (The Pile)

Max Activating Token Index: 162

Text #3

Max Range: 0.1917. Min Range: -0.1917

Max Act: 0.1813. Min Act: -0.0000

Data Index: 1738929 (The Pile)

Max Activating Token Index: 734

Text #4

Max Range: 0.1917. Min Range: -0.1917

Max Act: 0.1745. Min Act: -0.0000

Data Index: 1478832 (The Pile)

Max Activating Token Index: 441

Text #5

Max Range: 0.1917. Min Range: -0.1917

Max Act: 0.1861. Min Act: -0.0000

Data Index: 1841316 (The Pile)

Max Activating Token Index: 64

Text #6

Max Range: 0.1917. Min Range: -0.1917

Max Act: 0.1751. Min Act: -0.0000

Data Index: 199294 (The Pile)

Max Activating Token Index: 99

Text #7

Max Range: 0.1917. Min Range: -0.1917

Max Act: 0.1713. Min Act: -0.0000

Data Index: 1826406 (The Pile)

Max Activating Token Index: 489

Text #8

Max Range: 0.1917. Min Range: -0.1917

Max Act: 0.1891. Min Act: -0.0000

Data Index: 27540 (The Pile)

Max Activating Token Index: 495

Text #9

Max Range: 0.1917. Min Range: -0.1917

Max Act: 0.1712. Min Act: -0.0000

Data Index: 1932087 (The Pile)

Max Activating Token Index: 408

Text #10

Max Range: 0.1917. Min Range: -0.1917

Max Act: 0.1917. Min Act: -0.0000

Data Index: 945247 (The Pile)

Max Activating Token Index: 696

Text #11

Max Range: 0.1917. Min Range: -0.1917

Max Act: 0.1635. Min Act: -0.0000

Data Index: 1443731 (The Pile)

Max Activating Token Index: 577

Text #12

Max Range: 0.1917. Min Range: -0.1917

Max Act: 0.1546. Min Act: -0.0000

Data Index: 1810241 (The Pile)

Max Activating Token Index: 815

Text #13

Max Range: 0.1917. Min Range: -0.1917

Max Act: 0.1539. Min Act: -0.0000

Data Index: 1829325 (The Pile)

Max Activating Token Index: 751

Text #14

Max Range: 0.1917. Min Range: -0.1917

Max Act: 0.1635. Min Act: -0.0000

Data Index: 1009714 (The Pile)

Max Activating Token Index: 686

Text #15

Max Range: 0.1917. Min Range: -0.1917

Max Act: 0.1568. Min Act: -0.0000

Data Index: 1930612 (The Pile)

Max Activating Token Index: 719

Text #16

Max Range: 0.1917. Min Range: -0.1917

Max Act: 0.1555. Min Act: -0.0000

Data Index: 1799798 (The Pile)

Max Activating Token Index: 641

Text #17

Max Range: 0.1917. Min Range: -0.1917

Max Act: 0.1662. Min Act: -0.0000

Data Index: 1042551 (The Pile)

Max Activating Token Index: 775

Text #18

Max Range: 0.1917. Min Range: -0.1917

Max Act: 0.1558. Min Act: -0.0000

Data Index: 235275 (The Pile)

Max Activating Token Index: 135

Text #19

Max Range: 0.1917. Min Range: -0.1917

Max Act: 0.1750. Min Act: -0.0000

Data Index: 618802 (The Pile)

Max Activating Token Index: 702