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

Dataset: The Pile

Neuron 4102 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9690. Min Range: -0.9690

Max Act: 0.9384. Min Act: -0.0000

Data Index: 1980216 (The Pile)

Max Activating Token Index: 915

Text #1

Max Range: 0.9690. Min Range: -0.9690

Max Act: 0.9690. Min Act: -0.0000

Data Index: 1520724 (The Pile)

Max Activating Token Index: 848

Text #2

Max Range: 0.9690. Min Range: -0.9690

Max Act: 0.7807. Min Act: -0.0000

Data Index: 1306859 (The Pile)

Max Activating Token Index: 753

Text #3

Max Range: 0.9690. Min Range: -0.9690

Max Act: 0.8015. Min Act: -0.0000

Data Index: 256862 (The Pile)

Max Activating Token Index: 917

Text #4

Max Range: 0.9690. Min Range: -0.9690

Max Act: 0.7128. Min Act: -0.0000

Data Index: 141441 (The Pile)

Max Activating Token Index: 132

Text #5

Max Range: 0.9690. Min Range: -0.9690

Max Act: 0.7572. Min Act: -0.0000

Data Index: 222880 (The Pile)

Max Activating Token Index: 920

Text #6

Max Range: 0.9690. Min Range: -0.9690

Max Act: 0.7004. Min Act: -0.0000

Data Index: 1826545 (The Pile)

Max Activating Token Index: 953

Text #7

Max Range: 0.9690. Min Range: -0.9690

Max Act: 0.6571. Min Act: -0.0000

Data Index: 1596831 (The Pile)

Max Activating Token Index: 994

Text #8

Max Range: 0.9690. Min Range: -0.9690

Max Act: 0.6483. Min Act: -0.0000

Data Index: 1450388 (The Pile)

Max Activating Token Index: 425

Text #9

Max Range: 0.9690. Min Range: -0.9690

Max Act: 0.6469. Min Act: -0.0000

Data Index: 1487902 (The Pile)

Max Activating Token Index: 191

Text #10

Max Range: 0.9690. Min Range: -0.9690

Max Act: 0.6278. Min Act: -0.0000

Data Index: 1170345 (The Pile)

Max Activating Token Index: 760

Text #11

Max Range: 0.9690. Min Range: -0.9690

Max Act: 0.5528. Min Act: -0.0000

Data Index: 754937 (The Pile)

Max Activating Token Index: 1016

Text #12

Max Range: 0.9690. Min Range: -0.9690

Max Act: 0.5478. Min Act: -0.0000

Data Index: 239833 (The Pile)

Max Activating Token Index: 738

Text #13

Max Range: 0.9690. Min Range: -0.9690

Max Act: 0.5790. Min Act: -0.0000

Data Index: 345736 (The Pile)

Max Activating Token Index: 134

Text #14

Max Range: 0.9690. Min Range: -0.9690

Max Act: 0.5317. Min Act: -0.0000

Data Index: 80810 (The Pile)

Max Activating Token Index: 294

Text #15

Max Range: 0.9690. Min Range: -0.9690

Max Act: 0.5251. Min Act: -0.0000

Data Index: 1992931 (The Pile)

Max Activating Token Index: 152

Text #16

Max Range: 0.9690. Min Range: -0.9690

Max Act: 0.4770. Min Act: -0.0000

Data Index: 759457 (The Pile)

Max Activating Token Index: 654

Text #17

Max Range: 0.9690. Min Range: -0.9690

Max Act: 0.4764. Min Act: -0.0000

Data Index: 923614 (The Pile)

Max Activating Token Index: 71

Text #18

Max Range: 0.9690. Min Range: -0.9690

Max Act: 0.4540. Min Act: -0.0000

Data Index: 1817490 (The Pile)

Max Activating Token Index: 330

Text #19

Max Range: 0.9690. Min Range: -0.9690

Max Act: 0.5045. Min Act: -0.0000

Data Index: 968158 (The Pile)

Max Activating Token Index: 306