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

Dataset: The Pile

Neuron 4296 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2540. Min Range: -0.2540

Max Act: 0.2503. Min Act: -0.0000

Data Index: 1387989 (The Pile)

Max Activating Token Index: 144

Text #1

Max Range: 0.2540. Min Range: -0.2540

Max Act: 0.2323. Min Act: -0.0000

Data Index: 1206987 (The Pile)

Max Activating Token Index: 873

Text #2

Max Range: 0.2540. Min Range: -0.2540

Max Act: 0.2383. Min Act: -0.0000

Data Index: 19361 (The Pile)

Max Activating Token Index: 264

Text #3

Max Range: 0.2540. Min Range: -0.2540

Max Act: 0.2540. Min Act: -0.0000

Data Index: 801309 (The Pile)

Max Activating Token Index: 832

Text #4

Max Range: 0.2540. Min Range: -0.2540

Max Act: 0.2200. Min Act: -0.0000

Data Index: 1080641 (The Pile)

Max Activating Token Index: 629

Text #5

Max Range: 0.2540. Min Range: -0.2540

Max Act: 0.1942. Min Act: -0.0000

Data Index: 1487428 (The Pile)

Max Activating Token Index: 820

Text #6

Max Range: 0.2540. Min Range: -0.2540

Max Act: 0.2067. Min Act: -0.0000

Data Index: 282996 (The Pile)

Max Activating Token Index: 901

Text #7

Max Range: 0.2540. Min Range: -0.2540

Max Act: 0.2058. Min Act: -0.0000

Data Index: 79533 (The Pile)

Max Activating Token Index: 989

Text #8

Max Range: 0.2540. Min Range: -0.2540

Max Act: 0.1966. Min Act: 0.0001

Data Index: 1147084 (The Pile)

Max Activating Token Index: 298

Text #9

Max Range: 0.2540. Min Range: -0.2540

Max Act: 0.1950. Min Act: 0.0000

Data Index: 310740 (The Pile)

Max Activating Token Index: 248

Text #10

Max Range: 0.2540. Min Range: -0.2540

Max Act: 0.1996. Min Act: 0.0000

Data Index: 285659 (The Pile)

Max Activating Token Index: 313

Text #11

Max Range: 0.2540. Min Range: -0.2540

Max Act: 0.2114. Min Act: -0.0000

Data Index: 75240 (The Pile)

Max Activating Token Index: 695

Text #12

Max Range: 0.2540. Min Range: -0.2540

Max Act: 0.2057. Min Act: 0.0000

Data Index: 1703223 (The Pile)

Max Activating Token Index: 534

Text #13

Max Range: 0.2540. Min Range: -0.2540

Max Act: 0.1874. Min Act: -0.0000

Data Index: 1483658 (The Pile)

Max Activating Token Index: 919

Text #14

Max Range: 0.2540. Min Range: -0.2540

Max Act: 0.1822. Min Act: -0.0000

Data Index: 474591 (The Pile)

Max Activating Token Index: 763

Text #15

Max Range: 0.2540. Min Range: -0.2540

Max Act: 0.1886. Min Act: -0.0000

Data Index: 773460 (The Pile)

Max Activating Token Index: 750

Text #16

Max Range: 0.2540. Min Range: -0.2540

Max Act: 0.1849. Min Act: -0.0000

Data Index: 1222683 (The Pile)

Max Activating Token Index: 388

Text #17

Max Range: 0.2540. Min Range: -0.2540

Max Act: 0.1849. Min Act: -0.0000

Data Index: 1828990 (The Pile)

Max Activating Token Index: 461

Text #18

Max Range: 0.2540. Min Range: -0.2540

Max Act: 0.1851. Min Act: -0.0000

Data Index: 268404 (The Pile)

Max Activating Token Index: 460

Text #19

Max Range: 0.2540. Min Range: -0.2540

Max Act: 0.1831. Min Act: -0.0000

Data Index: 1187732 (The Pile)

Max Activating Token Index: 138