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

Dataset: The Pile

Neuron 2341 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.6792. Min Range: -5.6792

Max Act: 5.4345. Min Act: -0.0000

Data Index: 1265179 (The Pile)

Max Activating Token Index: 868

Text #1

Max Range: 5.6792. Min Range: -5.6792

Max Act: 5.6001. Min Act: -0.0000

Data Index: 1931125 (The Pile)

Max Activating Token Index: 921

Text #2

Max Range: 5.6792. Min Range: -5.6792

Max Act: 5.6792. Min Act: -0.0000

Data Index: 411215 (The Pile)

Max Activating Token Index: 342

Text #3

Max Range: 5.6792. Min Range: -5.6792

Max Act: 5.1922. Min Act: -0.0000

Data Index: 1648892 (The Pile)

Max Activating Token Index: 660

Text #4

Max Range: 5.6792. Min Range: -5.6792

Max Act: 4.9397. Min Act: -0.0000

Data Index: 1045523 (The Pile)

Max Activating Token Index: 725

Text #5

Max Range: 5.6792. Min Range: -5.6792

Max Act: 5.2195. Min Act: -0.0000

Data Index: 1900067 (The Pile)

Max Activating Token Index: 885

Text #6

Max Range: 5.6792. Min Range: -5.6792

Max Act: 5.3360. Min Act: -0.0000

Data Index: 888437 (The Pile)

Max Activating Token Index: 380

Text #7

Max Range: 5.6792. Min Range: -5.6792

Max Act: 5.2055. Min Act: -0.0000

Data Index: 398784 (The Pile)

Max Activating Token Index: 867

Text #8

Max Range: 5.6792. Min Range: -5.6792

Max Act: 5.2047. Min Act: -0.0000

Data Index: 765808 (The Pile)

Max Activating Token Index: 659

Text #9

Max Range: 5.6792. Min Range: -5.6792

Max Act: 5.0688. Min Act: -0.0000

Data Index: 1896020 (The Pile)

Max Activating Token Index: 767

Text #10

Max Range: 5.6792. Min Range: -5.6792

Max Act: 3.9939. Min Act: -0.0000

Data Index: 999866 (The Pile)

Max Activating Token Index: 802

Text #11

Max Range: 5.6792. Min Range: -5.6792

Max Act: 5.2908. Min Act: -0.0000

Data Index: 1465960 (The Pile)

Max Activating Token Index: 477

Text #12

Max Range: 5.6792. Min Range: -5.6792

Max Act: 4.7417. Min Act: -0.0000

Data Index: 916930 (The Pile)

Max Activating Token Index: 692

Text #13

Max Range: 5.6792. Min Range: -5.6792

Max Act: 5.3767. Min Act: -0.0000

Data Index: 1643181 (The Pile)

Max Activating Token Index: 670

Text #14

Max Range: 5.6792. Min Range: -5.6792

Max Act: 5.0019. Min Act: -0.0000

Data Index: 1139965 (The Pile)

Max Activating Token Index: 791

Text #15

Max Range: 5.6792. Min Range: -5.6792

Max Act: 4.7552. Min Act: -0.0000

Data Index: 1742476 (The Pile)

Max Activating Token Index: 449

Text #16

Max Range: 5.6792. Min Range: -5.6792

Max Act: 4.8592. Min Act: -0.0000

Data Index: 1182618 (The Pile)

Max Activating Token Index: 818

Text #17

Max Range: 5.6792. Min Range: -5.6792

Max Act: 4.4660. Min Act: -0.0000

Data Index: 1483701 (The Pile)

Max Activating Token Index: 582

Text #18

Max Range: 5.6792. Min Range: -5.6792

Max Act: 5.1005. Min Act: -0.0000

Data Index: 1709421 (The Pile)

Max Activating Token Index: 754

Text #19

Max Range: 5.6792. Min Range: -5.6792

Max Act: 4.3021. Min Act: -0.0000

Data Index: 494919 (The Pile)

Max Activating Token Index: 760