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

Dataset: The Pile

Neuron 2229 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2813. Min Range: -0.2813

Max Act: 0.2760. Min Act: -0.0000

Data Index: 1979437 (The Pile)

Max Activating Token Index: 127

Text #1

Max Range: 0.2813. Min Range: -0.2813

Max Act: 0.2813. Min Act: -0.0000

Data Index: 1479548 (The Pile)

Max Activating Token Index: 239

Text #2

Max Range: 0.2813. Min Range: -0.2813

Max Act: 0.2530. Min Act: -0.0000

Data Index: 1277727 (The Pile)

Max Activating Token Index: 605

Text #3

Max Range: 0.2813. Min Range: -0.2813

Max Act: 0.2517. Min Act: -0.0000

Data Index: 321056 (The Pile)

Max Activating Token Index: 816

Text #4

Max Range: 0.2813. Min Range: -0.2813

Max Act: 0.2380. Min Act: -0.0000

Data Index: 847185 (The Pile)

Max Activating Token Index: 278

Text #5

Max Range: 0.2813. Min Range: -0.2813

Max Act: 0.2276. Min Act: -0.0000

Data Index: 1309339 (The Pile)

Max Activating Token Index: 336

Text #6

Max Range: 0.2813. Min Range: -0.2813

Max Act: 0.2284. Min Act: -0.0000

Data Index: 1346699 (The Pile)

Max Activating Token Index: 126

Text #7

Max Range: 0.2813. Min Range: -0.2813

Max Act: 0.2218. Min Act: -0.0000

Data Index: 423916 (The Pile)

Max Activating Token Index: 125

Text #8

Max Range: 0.2813. Min Range: -0.2813

Max Act: 0.2223. Min Act: -0.0000

Data Index: 701039 (The Pile)

Max Activating Token Index: 13

Text #9

Max Range: 0.2813. Min Range: -0.2813

Max Act: 0.2156. Min Act: -0.0000

Data Index: 1695908 (The Pile)

Max Activating Token Index: 729

Text #10

Max Range: 0.2813. Min Range: -0.2813

Max Act: 0.2069. Min Act: -0.0000

Data Index: 653116 (The Pile)

Max Activating Token Index: 105

Text #11

Max Range: 0.2813. Min Range: -0.2813

Max Act: 0.2055. Min Act: -0.0000

Data Index: 887403 (The Pile)

Max Activating Token Index: 71

Text #12

Max Range: 0.2813. Min Range: -0.2813

Max Act: 0.2039. Min Act: -0.0000

Data Index: 1146575 (The Pile)

Max Activating Token Index: 190

Text #13

Max Range: 0.2813. Min Range: -0.2813

Max Act: 0.2105. Min Act: -0.0000

Data Index: 1231627 (The Pile)

Max Activating Token Index: 279

Text #14

Max Range: 0.2813. Min Range: -0.2813

Max Act: 0.2035. Min Act: -0.0001

Data Index: 1031591 (The Pile)

Max Activating Token Index: 435

Text #15

Max Range: 0.2813. Min Range: -0.2813

Max Act: 0.1995. Min Act: -0.0000

Data Index: 1173457 (The Pile)

Max Activating Token Index: 809

Text #16

Max Range: 0.2813. Min Range: -0.2813

Max Act: 0.1997. Min Act: -0.0000

Data Index: 1252373 (The Pile)

Max Activating Token Index: 170

Text #17

Max Range: 0.2813. Min Range: -0.2813

Max Act: 0.1929. Min Act: -0.0000

Data Index: 230670 (The Pile)

Max Activating Token Index: 869

Text #18

Max Range: 0.2813. Min Range: -0.2813

Max Act: 0.1912. Min Act: -0.0000

Data Index: 468930 (The Pile)

Max Activating Token Index: 296

Text #19

Max Range: 0.2813. Min Range: -0.2813

Max Act: 0.2115. Min Act: -0.0000

Data Index: 584711 (The Pile)

Max Activating Token Index: 308