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

Dataset: The Pile

Neuron 2447 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: 0.3794. Min Range: -0.3794

Max Act: 0.3794. Min Act: -0.0000

Data Index: 1374451 (The Pile)

Max Activating Token Index: 984

Text #1

Max Range: 0.3794. Min Range: -0.3794

Max Act: 0.2699. Min Act: -0.0000

Data Index: 1909596 (The Pile)

Max Activating Token Index: 1013

Text #2

Max Range: 0.3794. Min Range: -0.3794

Max Act: 0.2324. Min Act: -0.0000

Data Index: 609116 (The Pile)

Max Activating Token Index: 915

Text #3

Max Range: 0.3794. Min Range: -0.3794

Max Act: 0.2055. Min Act: -0.0000

Data Index: 1754082 (The Pile)

Max Activating Token Index: 967

Text #4

Max Range: 0.3794. Min Range: -0.3794

Max Act: 0.1956. Min Act: -0.0000

Data Index: 499387 (The Pile)

Max Activating Token Index: 914

Text #5

Max Range: 0.3794. Min Range: -0.3794

Max Act: 0.1810. Min Act: -0.0000

Data Index: 327293 (The Pile)

Max Activating Token Index: 880

Text #6

Max Range: 0.3794. Min Range: -0.3794

Max Act: 0.2041. Min Act: -0.0000

Data Index: 1897654 (The Pile)

Max Activating Token Index: 722

Text #7

Max Range: 0.3794. Min Range: -0.3794

Max Act: 0.1859. Min Act: -0.0000

Data Index: 1932686 (The Pile)

Max Activating Token Index: 641

Text #8

Max Range: 0.3794. Min Range: -0.3794

Max Act: 0.1900. Min Act: -0.0000

Data Index: 1707150 (The Pile)

Max Activating Token Index: 1015

Text #9

Max Range: 0.3794. Min Range: -0.3794

Max Act: 0.1832. Min Act: -0.0000

Data Index: 1296967 (The Pile)

Max Activating Token Index: 426

Text #10

Max Range: 0.3794. Min Range: -0.3794

Max Act: 0.1815. Min Act: -0.0000

Data Index: 1720710 (The Pile)

Max Activating Token Index: 558

Text #11

Max Range: 0.3794. Min Range: -0.3794

Max Act: 0.1871. Min Act: -0.0000

Data Index: 1916671 (The Pile)

Max Activating Token Index: 535

Text #12

Max Range: 0.3794. Min Range: -0.3794

Max Act: 0.1812. Min Act: -0.0000

Data Index: 645339 (The Pile)

Max Activating Token Index: 484

Text #13

Max Range: 0.3794. Min Range: -0.3794

Max Act: 0.1887. Min Act: -0.0000

Data Index: 90551 (The Pile)

Max Activating Token Index: 708

Text #14

Max Range: 0.3794. Min Range: -0.3794

Max Act: 0.1817. Min Act: -0.0000

Data Index: 1298690 (The Pile)

Max Activating Token Index: 572

Text #15

Max Range: 0.3794. Min Range: -0.3794

Max Act: 0.1696. Min Act: -0.0000

Data Index: 1157263 (The Pile)

Max Activating Token Index: 539

Text #16

Max Range: 0.3794. Min Range: -0.3794

Max Act: 0.1782. Min Act: -0.0000

Data Index: 376735 (The Pile)

Max Activating Token Index: 547

Text #17

Max Range: 0.3794. Min Range: -0.3794

Max Act: 0.1863. Min Act: -0.0000

Data Index: 1057654 (The Pile)

Max Activating Token Index: 827

Text #18

Max Range: 0.3794. Min Range: -0.3794

Max Act: 0.1643. Min Act: -0.0000

Data Index: 404207 (The Pile)

Max Activating Token Index: 681

Text #19

Max Range: 0.3794. Min Range: -0.3794

Max Act: 0.1832. Min Act: -0.0000

Data Index: 1707916 (The Pile)

Max Activating Token Index: 385