Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 3519 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.5940. Min Range: -0.5940

Max Act: 0.5940. Min Act: -0.0000

Data Index: 1658252 (The Pile)

Max Activating Token Index: 406

Text #1

Max Range: 0.5940. Min Range: -0.5940

Max Act: 0.5931. Min Act: -0.0000

Data Index: 1768428 (The Pile)

Max Activating Token Index: 813

Text #2

Max Range: 0.5940. Min Range: -0.5940

Max Act: 0.4859. Min Act: -0.0000

Data Index: 1586979 (The Pile)

Max Activating Token Index: 442

Text #3

Max Range: 0.5940. Min Range: -0.5940

Max Act: 0.4304. Min Act: -0.0000

Data Index: 603904 (The Pile)

Max Activating Token Index: 78

Text #4

Max Range: 0.5940. Min Range: -0.5940

Max Act: 0.3962. Min Act: -0.0000

Data Index: 499932 (The Pile)

Max Activating Token Index: 28

Text #5

Max Range: 0.5940. Min Range: -0.5940

Max Act: 0.3819. Min Act: -0.0000

Data Index: 440783 (The Pile)

Max Activating Token Index: 93

Text #6

Max Range: 0.5940. Min Range: -0.5940

Max Act: 0.3990. Min Act: -0.0000

Data Index: 735635 (The Pile)

Max Activating Token Index: 282

Text #7

Max Range: 0.5940. Min Range: -0.5940

Max Act: 0.4092. Min Act: -0.0000

Data Index: 90357 (The Pile)

Max Activating Token Index: 605

Text #8

Max Range: 0.5940. Min Range: -0.5940

Max Act: 0.4084. Min Act: -0.0000

Data Index: 50797 (The Pile)

Max Activating Token Index: 427

Text #9

Max Range: 0.5940. Min Range: -0.5940

Max Act: 0.3697. Min Act: -0.0000

Data Index: 1092468 (The Pile)

Max Activating Token Index: 84

Text #10

Max Range: 0.5940. Min Range: -0.5940

Max Act: 0.3884. Min Act: -0.0000

Data Index: 435932 (The Pile)

Max Activating Token Index: 526

Text #11

Max Range: 0.5940. Min Range: -0.5940

Max Act: 0.3745. Min Act: -0.0000

Data Index: 1078458 (The Pile)

Max Activating Token Index: 555

Text #12

Max Range: 0.5940. Min Range: -0.5940

Max Act: 0.3766. Min Act: -0.0000

Data Index: 757898 (The Pile)

Max Activating Token Index: 779

Text #13

Max Range: 0.5940. Min Range: -0.5940

Max Act: 0.3989. Min Act: -0.0000

Data Index: 6682 (The Pile)

Max Activating Token Index: 309

Text #14

Max Range: 0.5940. Min Range: -0.5940

Max Act: 0.3814. Min Act: -0.0000

Data Index: 1086820 (The Pile)

Max Activating Token Index: 109

Text #15

Max Range: 0.5940. Min Range: -0.5940

Max Act: 0.3654. Min Act: -0.0000

Data Index: 408787 (The Pile)

Max Activating Token Index: 567

Text #16

Max Range: 0.5940. Min Range: -0.5940

Max Act: 0.3647. Min Act: -0.0000

Data Index: 1577826 (The Pile)

Max Activating Token Index: 573

Text #17

Max Range: 0.5940. Min Range: -0.5940

Max Act: 0.3595. Min Act: -0.0000

Data Index: 1272620 (The Pile)

Max Activating Token Index: 352

Text #18

Max Range: 0.5940. Min Range: -0.5940

Max Act: 0.3618. Min Act: -0.0000

Data Index: 957829 (The Pile)

Max Activating Token Index: 701

Text #19

Max Range: 0.5940. Min Range: -0.5940

Max Act: 0.3600. Min Act: -0.0000

Data Index: 1513387 (The Pile)

Max Activating Token Index: 890