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

Dataset: The Pile

Neuron 1613 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: 0.5709. Min Range: -0.5709

Max Act: 0.5709. Min Act: -0.0000

Data Index: 1162905 (The Pile)

Max Activating Token Index: 657

Text #1

Max Range: 0.5709. Min Range: -0.5709

Max Act: 0.5493. Min Act: -0.0000

Data Index: 1936787 (The Pile)

Max Activating Token Index: 928

Text #2

Max Range: 0.5709. Min Range: -0.5709

Max Act: 0.5600. Min Act: -0.0000

Data Index: 374504 (The Pile)

Max Activating Token Index: 392

Text #3

Max Range: 0.5709. Min Range: -0.5709

Max Act: 0.4838. Min Act: -0.0000

Data Index: 127490 (The Pile)

Max Activating Token Index: 37

Text #4

Max Range: 0.5709. Min Range: -0.5709

Max Act: 0.5126. Min Act: -0.0000

Data Index: 584499 (The Pile)

Max Activating Token Index: 325

Text #5

Max Range: 0.5709. Min Range: -0.5709

Max Act: 0.4582. Min Act: -0.0000

Data Index: 1169233 (The Pile)

Max Activating Token Index: 154

Text #6

Max Range: 0.5709. Min Range: -0.5709

Max Act: 0.4440. Min Act: -0.0000

Data Index: 1966008 (The Pile)

Max Activating Token Index: 112

Text #7

Max Range: 0.5709. Min Range: -0.5709

Max Act: 0.5007. Min Act: -0.0000

Data Index: 1988680 (The Pile)

Max Activating Token Index: 778

Text #8

Max Range: 0.5709. Min Range: -0.5709

Max Act: 0.4850. Min Act: -0.0000

Data Index: 191633 (The Pile)

Max Activating Token Index: 48

Text #9

Max Range: 0.5709. Min Range: -0.5709

Max Act: 0.5182. Min Act: -0.0000

Data Index: 273300 (The Pile)

Max Activating Token Index: 440

Text #10

Max Range: 0.5709. Min Range: -0.5709

Max Act: 0.4875. Min Act: -0.0000

Data Index: 354603 (The Pile)

Max Activating Token Index: 327

Text #11

Max Range: 0.5709. Min Range: -0.5709

Max Act: 0.4453. Min Act: -0.0000

Data Index: 982042 (The Pile)

Max Activating Token Index: 501

Text #12

Max Range: 0.5709. Min Range: -0.5709

Max Act: 0.4962. Min Act: -0.0000

Data Index: 252680 (The Pile)

Max Activating Token Index: 64

Text #13

Max Range: 0.5709. Min Range: -0.5709

Max Act: 0.4665. Min Act: -0.0000

Data Index: 1014966 (The Pile)

Max Activating Token Index: 180

Text #14

Max Range: 0.5709. Min Range: -0.5709

Max Act: 0.4551. Min Act: -0.0000

Data Index: 978802 (The Pile)

Max Activating Token Index: 53

Text #15

Max Range: 0.5709. Min Range: -0.5709

Max Act: 0.5249. Min Act: -0.0000

Data Index: 1730092 (The Pile)

Max Activating Token Index: 493

Text #16

Max Range: 0.5709. Min Range: -0.5709

Max Act: 0.4894. Min Act: -0.0000

Data Index: 765860 (The Pile)

Max Activating Token Index: 486

Text #17

Max Range: 0.5709. Min Range: -0.5709

Max Act: 0.4555. Min Act: -0.0000

Data Index: 877385 (The Pile)

Max Activating Token Index: 251

Text #18

Max Range: 0.5709. Min Range: -0.5709

Max Act: 0.4878. Min Act: -0.0000

Data Index: 996113 (The Pile)

Max Activating Token Index: 816

Text #19

Max Range: 0.5709. Min Range: -0.5709

Max Act: 0.5025. Min Act: -0.0000

Data Index: 420023 (The Pile)

Max Activating Token Index: 328