Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 2127 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.2670. Min Range: -0.2670

Max Act: 0.2670. Min Act: -0.0000

Data Index: 1040226 (The Pile)

Max Activating Token Index: 637

Text #1

Max Range: 0.2670. Min Range: -0.2670

Max Act: 0.2307. Min Act: -0.0000

Data Index: 884214 (The Pile)

Max Activating Token Index: 616

Text #2

Max Range: 0.2670. Min Range: -0.2670

Max Act: 0.1905. Min Act: -0.0000

Data Index: 219886 (The Pile)

Max Activating Token Index: 856

Text #3

Max Range: 0.2670. Min Range: -0.2670

Max Act: 0.1955. Min Act: -0.0000

Data Index: 435453 (The Pile)

Max Activating Token Index: 292

Text #4

Max Range: 0.2670. Min Range: -0.2670

Max Act: 0.1785. Min Act: -0.0000

Data Index: 598798 (The Pile)

Max Activating Token Index: 193

Text #5

Max Range: 0.2670. Min Range: -0.2670

Max Act: 0.1908. Min Act: -0.0000

Data Index: 1623884 (The Pile)

Max Activating Token Index: 953

Text #6

Max Range: 0.2670. Min Range: -0.2670

Max Act: 0.1883. Min Act: -0.0000

Data Index: 104900 (The Pile)

Max Activating Token Index: 934

Text #7

Max Range: 0.2670. Min Range: -0.2670

Max Act: 0.1795. Min Act: -0.0000

Data Index: 1838378 (The Pile)

Max Activating Token Index: 835

Text #8

Max Range: 0.2670. Min Range: -0.2670

Max Act: 0.2040. Min Act: -0.0000

Data Index: 1251726 (The Pile)

Max Activating Token Index: 31

Text #9

Max Range: 0.2670. Min Range: -0.2670

Max Act: 0.1965. Min Act: -0.0000

Data Index: 594068 (The Pile)

Max Activating Token Index: 667

Text #10

Max Range: 0.2670. Min Range: -0.2670

Max Act: 0.1865. Min Act: -0.0000

Data Index: 870848 (The Pile)

Max Activating Token Index: 440

Text #11

Max Range: 0.2670. Min Range: -0.2670

Max Act: 0.1874. Min Act: -0.0000

Data Index: 1763855 (The Pile)

Max Activating Token Index: 849

Text #12

Max Range: 0.2670. Min Range: -0.2670

Max Act: 0.1895. Min Act: -0.0000

Data Index: 154379 (The Pile)

Max Activating Token Index: 139

Text #13

Max Range: 0.2670. Min Range: -0.2670

Max Act: 0.1942. Min Act: -0.0000

Data Index: 783193 (The Pile)

Max Activating Token Index: 115

Text #14

Max Range: 0.2670. Min Range: -0.2670

Max Act: 0.1745. Min Act: -0.0000

Data Index: 1370444 (The Pile)

Max Activating Token Index: 396

Text #15

Max Range: 0.2670. Min Range: -0.2670

Max Act: 0.1585. Min Act: -0.0000

Data Index: 9856 (The Pile)

Max Activating Token Index: 635

Text #16

Max Range: 0.2670. Min Range: -0.2670

Max Act: 0.1890. Min Act: -0.0000

Data Index: 1775107 (The Pile)

Max Activating Token Index: 172

Text #17

Max Range: 0.2670. Min Range: -0.2670

Max Act: 0.1518. Min Act: -0.0000

Data Index: 1690543 (The Pile)

Max Activating Token Index: 91

Text #18

Max Range: 0.2670. Min Range: -0.2670

Max Act: 0.1599. Min Act: -0.0000

Data Index: 1279139 (The Pile)

Max Activating Token Index: 481

Text #19

Max Range: 0.2670. Min Range: -0.2670

Max Act: 0.1631. Min Act: -0.0000

Data Index: 1844599 (The Pile)

Max Activating Token Index: 1000