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

Dataset: The Pile

Neuron 775 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: 0.2660. Min Range: -0.2660

Max Act: 0.2660. Min Act: -0.0000

Data Index: 916542 (The Pile)

Max Activating Token Index: 196

Text #1

Max Range: 0.2660. Min Range: -0.2660

Max Act: 0.2167. Min Act: -0.0000

Data Index: 527766 (The Pile)

Max Activating Token Index: 802

Text #2

Max Range: 0.2660. Min Range: -0.2660

Max Act: 0.2272. Min Act: -0.0000

Data Index: 493329 (The Pile)

Max Activating Token Index: 798

Text #3

Max Range: 0.2660. Min Range: -0.2660

Max Act: 0.1888. Min Act: -0.0000

Data Index: 152084 (The Pile)

Max Activating Token Index: 182

Text #4

Max Range: 0.2660. Min Range: -0.2660

Max Act: 0.2015. Min Act: -0.0000

Data Index: 911997 (The Pile)

Max Activating Token Index: 212

Text #5

Max Range: 0.2660. Min Range: -0.2660

Max Act: 0.1972. Min Act: -0.0000

Data Index: 492986 (The Pile)

Max Activating Token Index: 176

Text #6

Max Range: 0.2660. Min Range: -0.2660

Max Act: 0.1921. Min Act: -0.0000

Data Index: 697147 (The Pile)

Max Activating Token Index: 467

Text #7

Max Range: 0.2660. Min Range: -0.2660

Max Act: 0.2009. Min Act: -0.0000

Data Index: 645777 (The Pile)

Max Activating Token Index: 771

Text #8

Max Range: 0.2660. Min Range: -0.2660

Max Act: 0.1790. Min Act: -0.0000

Data Index: 1909635 (The Pile)

Max Activating Token Index: 806

Text #9

Max Range: 0.2660. Min Range: -0.2660

Max Act: 0.1731. Min Act: -0.0000

Data Index: 1458147 (The Pile)

Max Activating Token Index: 128

Text #10

Max Range: 0.2660. Min Range: -0.2660

Max Act: 0.1888. Min Act: -0.0000

Data Index: 499247 (The Pile)

Max Activating Token Index: 93

Text #11

Max Range: 0.2660. Min Range: -0.2660

Max Act: 0.1892. Min Act: -0.0000

Data Index: 839875 (The Pile)

Max Activating Token Index: 417

Text #12

Max Range: 0.2660. Min Range: -0.2660

Max Act: 0.1760. Min Act: -0.0000

Data Index: 1649860 (The Pile)

Max Activating Token Index: 175

Text #13

Max Range: 0.2660. Min Range: -0.2660

Max Act: 0.1691. Min Act: -0.0000

Data Index: 1735837 (The Pile)

Max Activating Token Index: 247

Text #14

Max Range: 0.2660. Min Range: -0.2660

Max Act: 0.1632. Min Act: -0.0000

Data Index: 167863 (The Pile)

Max Activating Token Index: 329

Text #15

Max Range: 0.2660. Min Range: -0.2660

Max Act: 0.1918. Min Act: -0.0000

Data Index: 685336 (The Pile)

Max Activating Token Index: 798

Text #16

Max Range: 0.2660. Min Range: -0.2660

Max Act: 0.1788. Min Act: -0.0000

Data Index: 354201 (The Pile)

Max Activating Token Index: 287

Text #17

Max Range: 0.2660. Min Range: -0.2660

Max Act: 0.1738. Min Act: -0.0000

Data Index: 1270155 (The Pile)

Max Activating Token Index: 428

Text #18

Max Range: 0.2660. Min Range: -0.2660

Max Act: 0.1764. Min Act: -0.0000

Data Index: 1048168 (The Pile)

Max Activating Token Index: 226

Text #19

Max Range: 0.2660. Min Range: -0.2660

Max Act: 0.1628. Min Act: -0.0000

Data Index: 1880578 (The Pile)

Max Activating Token Index: 99