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

Dataset: The Pile

Neuron 3603 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: 0.2899. Min Range: -0.2899

Max Act: 0.2899. Min Act: -0.0000

Data Index: 1985308 (The Pile)

Max Activating Token Index: 888

Text #1

Max Range: 0.2899. Min Range: -0.2899

Max Act: 0.2278. Min Act: -0.0000

Data Index: 486836 (The Pile)

Max Activating Token Index: 827

Text #2

Max Range: 0.2899. Min Range: -0.2899

Max Act: 0.2207. Min Act: -0.0000

Data Index: 17789 (The Pile)

Max Activating Token Index: 797

Text #3

Max Range: 0.2899. Min Range: -0.2899

Max Act: 0.1995. Min Act: -0.0000

Data Index: 1524503 (The Pile)

Max Activating Token Index: 713

Text #4

Max Range: 0.2899. Min Range: -0.2899

Max Act: 0.2027. Min Act: -0.0000

Data Index: 402824 (The Pile)

Max Activating Token Index: 766

Text #5

Max Range: 0.2899. Min Range: -0.2899

Max Act: 0.1985. Min Act: -0.0000

Data Index: 110853 (The Pile)

Max Activating Token Index: 696

Text #6

Max Range: 0.2899. Min Range: -0.2899

Max Act: 0.1833. Min Act: -0.0000

Data Index: 1293508 (The Pile)

Max Activating Token Index: 737

Text #7

Max Range: 0.2899. Min Range: -0.2899

Max Act: 0.1729. Min Act: -0.0000

Data Index: 1145129 (The Pile)

Max Activating Token Index: 406

Text #8

Max Range: 0.2899. Min Range: -0.2899

Max Act: 0.2305. Min Act: -0.0000

Data Index: 1912703 (The Pile)

Max Activating Token Index: 662

Text #9

Max Range: 0.2899. Min Range: -0.2899

Max Act: 0.1856. Min Act: -0.0000

Data Index: 1812833 (The Pile)

Max Activating Token Index: 368

Text #10

Max Range: 0.2899. Min Range: -0.2899

Max Act: 0.1930. Min Act: -0.0000

Data Index: 1881540 (The Pile)

Max Activating Token Index: 149

Text #11

Max Range: 0.2899. Min Range: -0.2899

Max Act: 0.2042. Min Act: -0.0000

Data Index: 925339 (The Pile)

Max Activating Token Index: 704

Text #12

Max Range: 0.2899. Min Range: -0.2899

Max Act: 0.1903. Min Act: -0.0000

Data Index: 151292 (The Pile)

Max Activating Token Index: 124

Text #13

Max Range: 0.2899. Min Range: -0.2899

Max Act: 0.1896. Min Act: -0.0000

Data Index: 1968541 (The Pile)

Max Activating Token Index: 286

Text #14

Max Range: 0.2899. Min Range: -0.2899

Max Act: 0.1630. Min Act: -0.0000

Data Index: 1785112 (The Pile)

Max Activating Token Index: 1019

Text #15

Max Range: 0.2899. Min Range: -0.2899

Max Act: 0.1853. Min Act: -0.0000

Data Index: 1817425 (The Pile)

Max Activating Token Index: 791

Text #16

Max Range: 0.2899. Min Range: -0.2899

Max Act: 0.1883. Min Act: -0.0000

Data Index: 1430306 (The Pile)

Max Activating Token Index: 371

Text #17

Max Range: 0.2899. Min Range: -0.2899

Max Act: 0.1853. Min Act: -0.0000

Data Index: 592326 (The Pile)

Max Activating Token Index: 829

Text #18

Max Range: 0.2899. Min Range: -0.2899

Max Act: 0.1839. Min Act: -0.0000

Data Index: 402803 (The Pile)

Max Activating Token Index: 157

Text #19

Max Range: 0.2899. Min Range: -0.2899

Max Act: 0.1784. Min Act: -0.0000

Data Index: 1601649 (The Pile)

Max Activating Token Index: 352