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

Dataset: The Pile

Neuron 4268 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: 5.6189. Min Range: -5.6189

Max Act: 5.6189. Min Act: -0.0000

Data Index: 53180 (The Pile)

Max Activating Token Index: 223

Text #1

Max Range: 5.6189. Min Range: -5.6189

Max Act: 4.1890. Min Act: -0.0000

Data Index: 1410557 (The Pile)

Max Activating Token Index: 788

Text #2

Max Range: 5.6189. Min Range: -5.6189

Max Act: 4.1903. Min Act: -0.0000

Data Index: 1321831 (The Pile)

Max Activating Token Index: 658

Text #3

Max Range: 5.6189. Min Range: -5.6189

Max Act: 3.5925. Min Act: -0.0000

Data Index: 627130 (The Pile)

Max Activating Token Index: 622

Text #4

Max Range: 5.6189. Min Range: -5.6189

Max Act: 3.2766. Min Act: -0.0000

Data Index: 1420633 (The Pile)

Max Activating Token Index: 924

Text #5

Max Range: 5.6189. Min Range: -5.6189

Max Act: 3.3026. Min Act: -0.0000

Data Index: 830722 (The Pile)

Max Activating Token Index: 275

Text #6

Max Range: 5.6189. Min Range: -5.6189

Max Act: 2.9498. Min Act: -0.0000

Data Index: 1708597 (The Pile)

Max Activating Token Index: 1000

Text #7

Max Range: 5.6189. Min Range: -5.6189

Max Act: 3.5723. Min Act: -0.0000

Data Index: 1690489 (The Pile)

Max Activating Token Index: 756

Text #8

Max Range: 5.6189. Min Range: -5.6189

Max Act: 3.4218. Min Act: -0.0000

Data Index: 1083098 (The Pile)

Max Activating Token Index: 268

Text #9

Max Range: 5.6189. Min Range: -5.6189

Max Act: 3.7268. Min Act: -0.0000

Data Index: 48734 (The Pile)

Max Activating Token Index: 884

Text #10

Max Range: 5.6189. Min Range: -5.6189

Max Act: 2.7073. Min Act: -0.0000

Data Index: 629660 (The Pile)

Max Activating Token Index: 556

Text #11

Max Range: 5.6189. Min Range: -5.6189

Max Act: 2.7212. Min Act: -0.0000

Data Index: 438418 (The Pile)

Max Activating Token Index: 725

Text #12

Max Range: 5.6189. Min Range: -5.6189

Max Act: 2.7162. Min Act: -0.0000

Data Index: 883728 (The Pile)

Max Activating Token Index: 610

Text #13

Max Range: 5.6189. Min Range: -5.6189

Max Act: 2.7859. Min Act: -0.0000

Data Index: 1962964 (The Pile)

Max Activating Token Index: 145

Text #14

Max Range: 5.6189. Min Range: -5.6189

Max Act: 2.5690. Min Act: -0.0000

Data Index: 1864736 (The Pile)

Max Activating Token Index: 94

Text #15

Max Range: 5.6189. Min Range: -5.6189

Max Act: 2.5627. Min Act: 0.0000

Data Index: 1563117 (The Pile)

Max Activating Token Index: 482

Text #16

Max Range: 5.6189. Min Range: -5.6189

Max Act: 2.6953. Min Act: -0.0000

Data Index: 655182 (The Pile)

Max Activating Token Index: 320

Text #17

Max Range: 5.6189. Min Range: -5.6189

Max Act: 2.4065. Min Act: -0.0000

Data Index: 788623 (The Pile)

Max Activating Token Index: 745

Text #18

Max Range: 5.6189. Min Range: -5.6189

Max Act: 2.4360. Min Act: -0.0000

Data Index: 872710 (The Pile)

Max Activating Token Index: 413

Text #19

Max Range: 5.6189. Min Range: -5.6189

Max Act: 2.2843. Min Act: -0.0000

Data Index: 1726589 (The Pile)

Max Activating Token Index: 852