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

Dataset: The Pile

Neuron 1872 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: 0.5891. Min Range: -0.5891

Max Act: 0.4925. Min Act: -0.0000

Data Index: 1124349 (The Pile)

Max Activating Token Index: 963

Text #1

Max Range: 0.5891. Min Range: -0.5891

Max Act: 0.5891. Min Act: -0.0000

Data Index: 941078 (The Pile)

Max Activating Token Index: 218

Text #2

Max Range: 0.5891. Min Range: -0.5891

Max Act: 0.5532. Min Act: -0.0000

Data Index: 1785600 (The Pile)

Max Activating Token Index: 988

Text #3

Max Range: 0.5891. Min Range: -0.5891

Max Act: 0.5201. Min Act: -0.0000

Data Index: 136267 (The Pile)

Max Activating Token Index: 101

Text #4

Max Range: 0.5891. Min Range: -0.5891

Max Act: 0.5201. Min Act: -0.0000

Data Index: 83315 (The Pile)

Max Activating Token Index: 52

Text #5

Max Range: 0.5891. Min Range: -0.5891

Max Act: 0.5326. Min Act: -0.0000

Data Index: 1868678 (The Pile)

Max Activating Token Index: 63

Text #6

Max Range: 0.5891. Min Range: -0.5891

Max Act: 0.5357. Min Act: -0.0000

Data Index: 903330 (The Pile)

Max Activating Token Index: 94

Text #7

Max Range: 0.5891. Min Range: -0.5891

Max Act: 0.5838. Min Act: -0.0000

Data Index: 1038362 (The Pile)

Max Activating Token Index: 79

Text #8

Max Range: 0.5891. Min Range: -0.5891

Max Act: 0.4099. Min Act: -0.0000

Data Index: 1498092 (The Pile)

Max Activating Token Index: 790

Text #9

Max Range: 0.5891. Min Range: -0.5891

Max Act: 0.5130. Min Act: -0.0000

Data Index: 308540 (The Pile)

Max Activating Token Index: 39

Text #10

Max Range: 0.5891. Min Range: -0.5891

Max Act: 0.5069. Min Act: -0.0000

Data Index: 1693667 (The Pile)

Max Activating Token Index: 431

Text #11

Max Range: 0.5891. Min Range: -0.5891

Max Act: 0.5371. Min Act: -0.0000

Data Index: 1009142 (The Pile)

Max Activating Token Index: 253

Text #12

Max Range: 0.5891. Min Range: -0.5891

Max Act: 0.4915. Min Act: -0.0000

Data Index: 1134589 (The Pile)

Max Activating Token Index: 935

Text #13

Max Range: 0.5891. Min Range: -0.5891

Max Act: 0.5018. Min Act: -0.0000

Data Index: 492715 (The Pile)

Max Activating Token Index: 785

Text #14

Max Range: 0.5891. Min Range: -0.5891

Max Act: 0.4820. Min Act: -0.0000

Data Index: 198420 (The Pile)

Max Activating Token Index: 753

Text #15

Max Range: 0.5891. Min Range: -0.5891

Max Act: 0.4909. Min Act: -0.0000

Data Index: 1929401 (The Pile)

Max Activating Token Index: 772

Text #16

Max Range: 0.5891. Min Range: -0.5891

Max Act: 0.4888. Min Act: -0.0000

Data Index: 1735139 (The Pile)

Max Activating Token Index: 429

Text #17

Max Range: 0.5891. Min Range: -0.5891

Max Act: 0.4552. Min Act: -0.0000

Data Index: 636484 (The Pile)

Max Activating Token Index: 183

Text #18

Max Range: 0.5891. Min Range: -0.5891

Max Act: 0.4848. Min Act: -0.0000

Data Index: 1151646 (The Pile)

Max Activating Token Index: 603

Text #19

Max Range: 0.5891. Min Range: -0.5891

Max Act: 0.5031. Min Act: -0.0000

Data Index: 559533 (The Pile)

Max Activating Token Index: 98