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

Dataset: The Pile

Neuron 3060 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: 3.4504. Min Range: -3.4504

Max Act: 3.3125. Min Act: -0.0000

Data Index: 1737456 (The Pile)

Max Activating Token Index: 654

Text #1

Max Range: 3.4504. Min Range: -3.4504

Max Act: 3.4504. Min Act: -0.0000

Data Index: 268143 (The Pile)

Max Activating Token Index: 449

Text #2

Max Range: 3.4504. Min Range: -3.4504

Max Act: 2.0686. Min Act: -0.0000

Data Index: 1769560 (The Pile)

Max Activating Token Index: 948

Text #3

Max Range: 3.4504. Min Range: -3.4504

Max Act: 2.0108. Min Act: -0.0000

Data Index: 256095 (The Pile)

Max Activating Token Index: 654

Text #4

Max Range: 3.4504. Min Range: -3.4504

Max Act: 2.2136. Min Act: -0.0000

Data Index: 1335579 (The Pile)

Max Activating Token Index: 838

Text #5

Max Range: 3.4504. Min Range: -3.4504

Max Act: 1.7913. Min Act: -0.0000

Data Index: 968302 (The Pile)

Max Activating Token Index: 822

Text #6

Max Range: 3.4504. Min Range: -3.4504

Max Act: 1.8132. Min Act: -0.0000

Data Index: 872379 (The Pile)

Max Activating Token Index: 878

Text #7

Max Range: 3.4504. Min Range: -3.4504

Max Act: 1.6359. Min Act: -0.0000

Data Index: 1390597 (The Pile)

Max Activating Token Index: 962

Text #8

Max Range: 3.4504. Min Range: -3.4504

Max Act: 1.6435. Min Act: -0.0000

Data Index: 564377 (The Pile)

Max Activating Token Index: 300

Text #9

Max Range: 3.4504. Min Range: -3.4504

Max Act: 1.6918. Min Act: -0.0000

Data Index: 1083643 (The Pile)

Max Activating Token Index: 851

Text #10

Max Range: 3.4504. Min Range: -3.4504

Max Act: 1.7624. Min Act: -0.0000

Data Index: 638014 (The Pile)

Max Activating Token Index: 466

Text #11

Max Range: 3.4504. Min Range: -3.4504

Max Act: 2.0111. Min Act: -0.0000

Data Index: 164134 (The Pile)

Max Activating Token Index: 839

Text #12

Max Range: 3.4504. Min Range: -3.4504

Max Act: 1.3882. Min Act: -0.0000

Data Index: 75677 (The Pile)

Max Activating Token Index: 659

Text #13

Max Range: 3.4504. Min Range: -3.4504

Max Act: 1.4505. Min Act: -0.0000

Data Index: 1292451 (The Pile)

Max Activating Token Index: 256

Text #14

Max Range: 3.4504. Min Range: -3.4504

Max Act: 1.5478. Min Act: -0.0000

Data Index: 1129067 (The Pile)

Max Activating Token Index: 792

Text #15

Max Range: 3.4504. Min Range: -3.4504

Max Act: 1.6226. Min Act: -0.0000

Data Index: 1088443 (The Pile)

Max Activating Token Index: 719

Text #16

Max Range: 3.4504. Min Range: -3.4504

Max Act: 1.4106. Min Act: -0.0000

Data Index: 1626517 (The Pile)

Max Activating Token Index: 76

Text #17

Max Range: 3.4504. Min Range: -3.4504

Max Act: 1.4174. Min Act: -0.0000

Data Index: 327618 (The Pile)

Max Activating Token Index: 945

Text #18

Max Range: 3.4504. Min Range: -3.4504

Max Act: 1.4015. Min Act: -0.0000

Data Index: 959717 (The Pile)

Max Activating Token Index: 231

Text #19

Max Range: 3.4504. Min Range: -3.4504

Max Act: 1.4713. Min Act: 0.0000

Data Index: 1503948 (The Pile)

Max Activating Token Index: 337