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

Dataset: The Pile

Neuron 2654 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: 1.7727. Min Range: -1.7727

Max Act: 1.7727. Min Act: -0.0000

Data Index: 1441067 (The Pile)

Max Activating Token Index: 855

Text #1

Max Range: 1.7727. Min Range: -1.7727

Max Act: 1.5668. Min Act: -0.0000

Data Index: 1212130 (The Pile)

Max Activating Token Index: 942

Text #2

Max Range: 1.7727. Min Range: -1.7727

Max Act: 1.5584. Min Act: -0.0000

Data Index: 1794673 (The Pile)

Max Activating Token Index: 808

Text #3

Max Range: 1.7727. Min Range: -1.7727

Max Act: 1.4467. Min Act: -0.0000

Data Index: 564504 (The Pile)

Max Activating Token Index: 867

Text #4

Max Range: 1.7727. Min Range: -1.7727

Max Act: 1.4862. Min Act: -0.0000

Data Index: 766244 (The Pile)

Max Activating Token Index: 656

Text #5

Max Range: 1.7727. Min Range: -1.7727

Max Act: 1.4888. Min Act: -0.0000

Data Index: 1767829 (The Pile)

Max Activating Token Index: 161

Text #6

Max Range: 1.7727. Min Range: -1.7727

Max Act: 1.4921. Min Act: -0.0000

Data Index: 594051 (The Pile)

Max Activating Token Index: 1019

Text #7

Max Range: 1.7727. Min Range: -1.7727

Max Act: 1.4777. Min Act: 0.0000

Data Index: 1098135 (The Pile)

Max Activating Token Index: 478

Text #8

Max Range: 1.7727. Min Range: -1.7727

Max Act: 1.4590. Min Act: -0.0000

Data Index: 513238 (The Pile)

Max Activating Token Index: 524

Text #9

Max Range: 1.7727. Min Range: -1.7727

Max Act: 1.4605. Min Act: -0.0000

Data Index: 1267924 (The Pile)

Max Activating Token Index: 687

Text #10

Max Range: 1.7727. Min Range: -1.7727

Max Act: 1.4129. Min Act: 0.0000

Data Index: 1131758 (The Pile)

Max Activating Token Index: 984

Text #11

Max Range: 1.7727. Min Range: -1.7727

Max Act: 1.3196. Min Act: -0.0000

Data Index: 1968827 (The Pile)

Max Activating Token Index: 579

Text #12

Max Range: 1.7727. Min Range: -1.7727

Max Act: 1.3793. Min Act: -0.0000

Data Index: 378852 (The Pile)

Max Activating Token Index: 1015

Text #13

Max Range: 1.7727. Min Range: -1.7727

Max Act: 1.2841. Min Act: -0.0000

Data Index: 190548 (The Pile)

Max Activating Token Index: 543

Text #14

Max Range: 1.7727. Min Range: -1.7727

Max Act: 1.4446. Min Act: -0.0000

Data Index: 783469 (The Pile)

Max Activating Token Index: 545

Text #15

Max Range: 1.7727. Min Range: -1.7727

Max Act: 1.3497. Min Act: -0.0000

Data Index: 145547 (The Pile)

Max Activating Token Index: 279

Text #16

Max Range: 1.7727. Min Range: -1.7727

Max Act: 1.4311. Min Act: -0.0000

Data Index: 1889494 (The Pile)

Max Activating Token Index: 380

Text #17

Max Range: 1.7727. Min Range: -1.7727

Max Act: 1.3456. Min Act: -0.0000

Data Index: 1931008 (The Pile)

Max Activating Token Index: 993

Text #18

Max Range: 1.7727. Min Range: -1.7727

Max Act: 1.2654. Min Act: -0.0000

Data Index: 1235865 (The Pile)

Max Activating Token Index: 168

Text #19

Max Range: 1.7727. Min Range: -1.7727

Max Act: 1.3065. Min Act: -0.0000

Data Index: 1843383 (The Pile)

Max Activating Token Index: 964