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

Dataset: The Pile

Neuron 1852 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: 0.8783. Min Range: -0.8783

Max Act: 0.8783. Min Act: -0.0000

Data Index: 533099 (The Pile)

Max Activating Token Index: 912

Text #1

Max Range: 0.8783. Min Range: -0.8783

Max Act: 0.7840. Min Act: -0.0000

Data Index: 114457 (The Pile)

Max Activating Token Index: 370

Text #2

Max Range: 0.8783. Min Range: -0.8783

Max Act: 0.7467. Min Act: -0.0000

Data Index: 1309749 (The Pile)

Max Activating Token Index: 832

Text #3

Max Range: 0.8783. Min Range: -0.8783

Max Act: 0.8400. Min Act: -0.0000

Data Index: 1798772 (The Pile)

Max Activating Token Index: 960

Text #4

Max Range: 0.8783. Min Range: -0.8783

Max Act: 0.7487. Min Act: -0.0000

Data Index: 1451844 (The Pile)

Max Activating Token Index: 1019

Text #5

Max Range: 0.8783. Min Range: -0.8783

Max Act: 0.7352. Min Act: -0.0000

Data Index: 1072530 (The Pile)

Max Activating Token Index: 964

Text #6

Max Range: 0.8783. Min Range: -0.8783

Max Act: 0.6482. Min Act: -0.0000

Data Index: 1650548 (The Pile)

Max Activating Token Index: 456

Text #7

Max Range: 0.8783. Min Range: -0.8783

Max Act: 0.6310. Min Act: -0.0000

Data Index: 1794666 (The Pile)

Max Activating Token Index: 923

Text #8

Max Range: 0.8783. Min Range: -0.8783

Max Act: 0.6396. Min Act: -0.0000

Data Index: 186030 (The Pile)

Max Activating Token Index: 961

Text #9

Max Range: 0.8783. Min Range: -0.8783

Max Act: 0.6579. Min Act: -0.0000

Data Index: 905015 (The Pile)

Max Activating Token Index: 836

Text #10

Max Range: 0.8783. Min Range: -0.8783

Max Act: 0.6762. Min Act: -0.0000

Data Index: 1895709 (The Pile)

Max Activating Token Index: 822

Text #11

Max Range: 0.8783. Min Range: -0.8783

Max Act: 0.6287. Min Act: -0.0000

Data Index: 1060538 (The Pile)

Max Activating Token Index: 470

Text #12

Max Range: 0.8783. Min Range: -0.8783

Max Act: 0.6246. Min Act: -0.0000

Data Index: 844029 (The Pile)

Max Activating Token Index: 285

Text #13

Max Range: 0.8783. Min Range: -0.8783

Max Act: 0.6239. Min Act: -0.0000

Data Index: 1338821 (The Pile)

Max Activating Token Index: 437

Text #14

Max Range: 0.8783. Min Range: -0.8783

Max Act: 0.6467. Min Act: -0.0000

Data Index: 1874067 (The Pile)

Max Activating Token Index: 898

Text #15

Max Range: 0.8783. Min Range: -0.8783

Max Act: 0.6404. Min Act: -0.0000

Data Index: 1075714 (The Pile)

Max Activating Token Index: 638

Text #16

Max Range: 0.8783. Min Range: -0.8783

Max Act: 0.5982. Min Act: -0.0000

Data Index: 402812 (The Pile)

Max Activating Token Index: 878

Text #17

Max Range: 0.8783. Min Range: -0.8783

Max Act: 0.6209. Min Act: -0.0000

Data Index: 1756317 (The Pile)

Max Activating Token Index: 797

Text #18

Max Range: 0.8783. Min Range: -0.8783

Max Act: 0.6175. Min Act: -0.0000

Data Index: 1583526 (The Pile)

Max Activating Token Index: 983

Text #19

Max Range: 0.8783. Min Range: -0.8783

Max Act: 0.5661. Min Act: -0.0000

Data Index: 1137407 (The Pile)

Max Activating Token Index: 80