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

Dataset: The Pile

Neuron 4768 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: 0.5240. Min Range: -0.5240

Max Act: 0.5240. Min Act: -0.0000

Data Index: 1141583 (The Pile)

Max Activating Token Index: 878

Text #1

Max Range: 0.5240. Min Range: -0.5240

Max Act: 0.4968. Min Act: -0.0000

Data Index: 722865 (The Pile)

Max Activating Token Index: 54

Text #2

Max Range: 0.5240. Min Range: -0.5240

Max Act: 0.3955. Min Act: -0.0000

Data Index: 1517874 (The Pile)

Max Activating Token Index: 877

Text #3

Max Range: 0.5240. Min Range: -0.5240

Max Act: 0.3445. Min Act: -0.0000

Data Index: 1627576 (The Pile)

Max Activating Token Index: 334

Text #4

Max Range: 0.5240. Min Range: -0.5240

Max Act: 0.3207. Min Act: -0.0000

Data Index: 1933237 (The Pile)

Max Activating Token Index: 738

Text #5

Max Range: 0.5240. Min Range: -0.5240

Max Act: 0.4354. Min Act: -0.0000

Data Index: 157023 (The Pile)

Max Activating Token Index: 353

Text #6

Max Range: 0.5240. Min Range: -0.5240

Max Act: 0.3551. Min Act: -0.0000

Data Index: 695858 (The Pile)

Max Activating Token Index: 501

Text #7

Max Range: 0.5240. Min Range: -0.5240

Max Act: 0.3590. Min Act: -0.0000

Data Index: 919894 (The Pile)

Max Activating Token Index: 148

Text #8

Max Range: 0.5240. Min Range: -0.5240

Max Act: 0.3575. Min Act: -0.0000

Data Index: 636366 (The Pile)

Max Activating Token Index: 865

Text #9

Max Range: 0.5240. Min Range: -0.5240

Max Act: 0.3539. Min Act: -0.0000

Data Index: 1642758 (The Pile)

Max Activating Token Index: 466

Text #10

Max Range: 0.5240. Min Range: -0.5240

Max Act: 0.3072. Min Act: -0.0000

Data Index: 1681770 (The Pile)

Max Activating Token Index: 914

Text #11

Max Range: 0.5240. Min Range: -0.5240

Max Act: 0.2795. Min Act: -0.0000

Data Index: 514766 (The Pile)

Max Activating Token Index: 27

Text #12

Max Range: 0.5240. Min Range: -0.5240

Max Act: 0.2527. Min Act: -0.0000

Data Index: 12126 (The Pile)

Max Activating Token Index: 783

Text #13

Max Range: 0.5240. Min Range: -0.5240

Max Act: 0.2653. Min Act: -0.0000

Data Index: 929855 (The Pile)

Max Activating Token Index: 1013

Text #14

Max Range: 0.5240. Min Range: -0.5240

Max Act: 0.2656. Min Act: -0.0000

Data Index: 996590 (The Pile)

Max Activating Token Index: 631

Text #15

Max Range: 0.5240. Min Range: -0.5240

Max Act: 0.3477. Min Act: -0.0000

Data Index: 1872569 (The Pile)

Max Activating Token Index: 786

Text #16

Max Range: 0.5240. Min Range: -0.5240

Max Act: 0.2640. Min Act: -0.0000

Data Index: 381757 (The Pile)

Max Activating Token Index: 238

Text #17

Max Range: 0.5240. Min Range: -0.5240

Max Act: 0.2782. Min Act: -0.0000

Data Index: 1217663 (The Pile)

Max Activating Token Index: 854

Text #18

Max Range: 0.5240. Min Range: -0.5240

Max Act: 0.2488. Min Act: -0.0000

Data Index: 477745 (The Pile)

Max Activating Token Index: 287

Text #19

Max Range: 0.5240. Min Range: -0.5240

Max Act: 0.2565. Min Act: -0.0000

Data Index: 810165 (The Pile)

Max Activating Token Index: 651