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

Dataset: The Pile

Neuron 3462 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: 0.2054. Min Range: -0.2054

Max Act: 0.2054. Min Act: -0.0000

Data Index: 955054 (The Pile)

Max Activating Token Index: 388

Text #1

Max Range: 0.2054. Min Range: -0.2054

Max Act: 0.1906. Min Act: -0.0000

Data Index: 1838656 (The Pile)

Max Activating Token Index: 59

Text #2

Max Range: 0.2054. Min Range: -0.2054

Max Act: 0.1947. Min Act: -0.0000

Data Index: 1847233 (The Pile)

Max Activating Token Index: 54

Text #3

Max Range: 0.2054. Min Range: -0.2054

Max Act: 0.2019. Min Act: -0.0000

Data Index: 531744 (The Pile)

Max Activating Token Index: 993

Text #4

Max Range: 0.2054. Min Range: -0.2054

Max Act: 0.1793. Min Act: -0.0000

Data Index: 577884 (The Pile)

Max Activating Token Index: 709

Text #5

Max Range: 0.2054. Min Range: -0.2054

Max Act: 0.2022. Min Act: -0.0000

Data Index: 1186682 (The Pile)

Max Activating Token Index: 557

Text #6

Max Range: 0.2054. Min Range: -0.2054

Max Act: 0.1841. Min Act: -0.0000

Data Index: 612316 (The Pile)

Max Activating Token Index: 352

Text #7

Max Range: 0.2054. Min Range: -0.2054

Max Act: 0.1802. Min Act: -0.0000

Data Index: 1883482 (The Pile)

Max Activating Token Index: 629

Text #8

Max Range: 0.2054. Min Range: -0.2054

Max Act: 0.1854. Min Act: -0.0000

Data Index: 1552091 (The Pile)

Max Activating Token Index: 68

Text #9

Max Range: 0.2054. Min Range: -0.2054

Max Act: 0.1886. Min Act: -0.0000

Data Index: 183890 (The Pile)

Max Activating Token Index: 850

Text #10

Max Range: 0.2054. Min Range: -0.2054

Max Act: 0.1780. Min Act: -0.0000

Data Index: 1923816 (The Pile)

Max Activating Token Index: 456

Text #11

Max Range: 0.2054. Min Range: -0.2054

Max Act: 0.1946. Min Act: -0.0000

Data Index: 613444 (The Pile)

Max Activating Token Index: 491

Text #12

Max Range: 0.2054. Min Range: -0.2054

Max Act: 0.1626. Min Act: -0.0000

Data Index: 1861412 (The Pile)

Max Activating Token Index: 906

Text #13

Max Range: 0.2054. Min Range: -0.2054

Max Act: 0.1556. Min Act: -0.0000

Data Index: 1174371 (The Pile)

Max Activating Token Index: 63

Text #14

Max Range: 0.2054. Min Range: -0.2054

Max Act: 0.1405. Min Act: -0.0000

Data Index: 1558925 (The Pile)

Max Activating Token Index: 868

Text #15

Max Range: 0.2054. Min Range: -0.2054

Max Act: 0.1706. Min Act: -0.0000

Data Index: 1845941 (The Pile)

Max Activating Token Index: 694

Text #16

Max Range: 0.2054. Min Range: -0.2054

Max Act: 0.1640. Min Act: -0.0000

Data Index: 1033924 (The Pile)

Max Activating Token Index: 264

Text #17

Max Range: 0.2054. Min Range: -0.2054

Max Act: 0.1637. Min Act: -0.0000

Data Index: 195094 (The Pile)

Max Activating Token Index: 334

Text #18

Max Range: 0.2054. Min Range: -0.2054

Max Act: 0.1574. Min Act: -0.0000

Data Index: 1603058 (The Pile)

Max Activating Token Index: 658

Text #19

Max Range: 0.2054. Min Range: -0.2054

Max Act: 0.1718. Min Act: -0.0000

Data Index: 1149721 (The Pile)

Max Activating Token Index: 214