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

Dataset: The Pile

Neuron 4610 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: 0.2819. Min Range: -0.2819

Max Act: 0.2539. Min Act: -0.0000

Data Index: 1679360 (The Pile)

Max Activating Token Index: 666

Text #1

Max Range: 0.2819. Min Range: -0.2819

Max Act: 0.2819. Min Act: -0.0000

Data Index: 1791947 (The Pile)

Max Activating Token Index: 612

Text #2

Max Range: 0.2819. Min Range: -0.2819

Max Act: 0.2345. Min Act: -0.0000

Data Index: 684721 (The Pile)

Max Activating Token Index: 350

Text #3

Max Range: 0.2819. Min Range: -0.2819

Max Act: 0.2307. Min Act: -0.0000

Data Index: 612932 (The Pile)

Max Activating Token Index: 981

Text #4

Max Range: 0.2819. Min Range: -0.2819

Max Act: 0.2318. Min Act: -0.0000

Data Index: 771148 (The Pile)

Max Activating Token Index: 310

Text #5

Max Range: 0.2819. Min Range: -0.2819

Max Act: 0.2159. Min Act: -0.0000

Data Index: 162817 (The Pile)

Max Activating Token Index: 879

Text #6

Max Range: 0.2819. Min Range: -0.2819

Max Act: 0.2058. Min Act: -0.0000

Data Index: 353378 (The Pile)

Max Activating Token Index: 442

Text #7

Max Range: 0.2819. Min Range: -0.2819

Max Act: 0.2005. Min Act: -0.0000

Data Index: 1401869 (The Pile)

Max Activating Token Index: 924

Text #8

Max Range: 0.2819. Min Range: -0.2819

Max Act: 0.2164. Min Act: -0.0000

Data Index: 1141166 (The Pile)

Max Activating Token Index: 956

Text #9

Max Range: 0.2819. Min Range: -0.2819

Max Act: 0.1913. Min Act: -0.0000

Data Index: 1341892 (The Pile)

Max Activating Token Index: 805

Text #10

Max Range: 0.2819. Min Range: -0.2819

Max Act: 0.2053. Min Act: -0.0000

Data Index: 1003527 (The Pile)

Max Activating Token Index: 629

Text #11

Max Range: 0.2819. Min Range: -0.2819

Max Act: 0.2001. Min Act: -0.0000

Data Index: 160998 (The Pile)

Max Activating Token Index: 692

Text #12

Max Range: 0.2819. Min Range: -0.2819

Max Act: 0.2038. Min Act: -0.0000

Data Index: 828108 (The Pile)

Max Activating Token Index: 208

Text #13

Max Range: 0.2819. Min Range: -0.2819

Max Act: 0.2041. Min Act: -0.0000

Data Index: 416620 (The Pile)

Max Activating Token Index: 333

Text #14

Max Range: 0.2819. Min Range: -0.2819

Max Act: 0.2055. Min Act: -0.0000

Data Index: 1764837 (The Pile)

Max Activating Token Index: 900

Text #15

Max Range: 0.2819. Min Range: -0.2819

Max Act: 0.2103. Min Act: -0.0000

Data Index: 1477423 (The Pile)

Max Activating Token Index: 423

Text #16

Max Range: 0.2819. Min Range: -0.2819

Max Act: 0.1868. Min Act: -0.0000

Data Index: 627972 (The Pile)

Max Activating Token Index: 521

Text #17

Max Range: 0.2819. Min Range: -0.2819

Max Act: 0.1942. Min Act: -0.0000

Data Index: 314511 (The Pile)

Max Activating Token Index: 768

Text #18

Max Range: 0.2819. Min Range: -0.2819

Max Act: 0.1891. Min Act: -0.0000

Data Index: 463673 (The Pile)

Max Activating Token Index: 426

Text #19

Max Range: 0.2819. Min Range: -0.2819

Max Act: 0.2124. Min Act: -0.0000

Data Index: 141810 (The Pile)

Max Activating Token Index: 757