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

Dataset: The Pile

Neuron 5009 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.8546. Min Range: -3.8546

Max Act: 3.8546. Min Act: -0.0000

Data Index: 1811933 (The Pile)

Max Activating Token Index: 872

Text #1

Max Range: 3.8546. Min Range: -3.8546

Max Act: 3.7017. Min Act: -0.0000

Data Index: 1812679 (The Pile)

Max Activating Token Index: 839

Text #2

Max Range: 3.8546. Min Range: -3.8546

Max Act: 3.8017. Min Act: -0.0000

Data Index: 1553706 (The Pile)

Max Activating Token Index: 271

Text #3

Max Range: 3.8546. Min Range: -3.8546

Max Act: 3.6615. Min Act: -0.0000

Data Index: 120814 (The Pile)

Max Activating Token Index: 707

Text #4

Max Range: 3.8546. Min Range: -3.8546

Max Act: 3.1948. Min Act: -0.0000

Data Index: 1640538 (The Pile)

Max Activating Token Index: 557

Text #5

Max Range: 3.8546. Min Range: -3.8546

Max Act: 2.9268. Min Act: -0.0000

Data Index: 614733 (The Pile)

Max Activating Token Index: 805

Text #6

Max Range: 3.8546. Min Range: -3.8546

Max Act: 2.7772. Min Act: -0.0000

Data Index: 68280 (The Pile)

Max Activating Token Index: 847

Text #7

Max Range: 3.8546. Min Range: -3.8546

Max Act: 2.0333. Min Act: -0.0000

Data Index: 144783 (The Pile)

Max Activating Token Index: 975

Text #8

Max Range: 3.8546. Min Range: -3.8546

Max Act: 0.8863. Min Act: -0.0000

Data Index: 1576957 (The Pile)

Max Activating Token Index: 129

Text #9

Max Range: 3.8546. Min Range: -3.8546

Max Act: 0.7880. Min Act: -0.0000

Data Index: 1501568 (The Pile)

Max Activating Token Index: 86

Text #10

Max Range: 3.8546. Min Range: -3.8546

Max Act: 0.8038. Min Act: -0.0000

Data Index: 922112 (The Pile)

Max Activating Token Index: 249

Text #11

Max Range: 3.8546. Min Range: -3.8546

Max Act: 0.7395. Min Act: -0.0000

Data Index: 905972 (The Pile)

Max Activating Token Index: 416

Text #12

Max Range: 3.8546. Min Range: -3.8546

Max Act: 0.8094. Min Act: -0.0000

Data Index: 951011 (The Pile)

Max Activating Token Index: 1010

Text #13

Max Range: 3.8546. Min Range: -3.8546

Max Act: 0.7451. Min Act: -0.0000

Data Index: 1317283 (The Pile)

Max Activating Token Index: 278

Text #14

Max Range: 3.8546. Min Range: -3.8546

Max Act: 0.7572. Min Act: -0.0000

Data Index: 1643568 (The Pile)

Max Activating Token Index: 470

Text #15

Max Range: 3.8546. Min Range: -3.8546

Max Act: 0.7825. Min Act: -0.0000

Data Index: 1625821 (The Pile)

Max Activating Token Index: 744

Text #16

Max Range: 3.8546. Min Range: -3.8546

Max Act: 0.7563. Min Act: -0.0000

Data Index: 1316257 (The Pile)

Max Activating Token Index: 445

Text #17

Max Range: 3.8546. Min Range: -3.8546

Max Act: 0.7057. Min Act: -0.0000

Data Index: 1218912 (The Pile)

Max Activating Token Index: 549

Text #18

Max Range: 3.8546. Min Range: -3.8546

Max Act: 0.7073. Min Act: -0.0000

Data Index: 1638627 (The Pile)

Max Activating Token Index: 884

Text #19

Max Range: 3.8546. Min Range: -3.8546

Max Act: 0.6700. Min Act: -0.0000

Data Index: 1021539 (The Pile)

Max Activating Token Index: 813