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

Dataset: The Pile

Neuron 1194 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1697. Min Range: -1.1697

Max Act: 1.1697. Min Act: -0.0000

Data Index: 207112 (The Pile)

Max Activating Token Index: 153

Text #1

Max Range: 1.1697. Min Range: -1.1697

Max Act: 0.9669. Min Act: -0.0000

Data Index: 1599364 (The Pile)

Max Activating Token Index: 33

Text #2

Max Range: 1.1697. Min Range: -1.1697

Max Act: 0.8730. Min Act: -0.0000

Data Index: 1270359 (The Pile)

Max Activating Token Index: 567

Text #3

Max Range: 1.1697. Min Range: -1.1697

Max Act: 0.9638. Min Act: -0.0000

Data Index: 795567 (The Pile)

Max Activating Token Index: 846

Text #4

Max Range: 1.1697. Min Range: -1.1697

Max Act: 0.9730. Min Act: -0.0000

Data Index: 1099575 (The Pile)

Max Activating Token Index: 480

Text #5

Max Range: 1.1697. Min Range: -1.1697

Max Act: 1.0026. Min Act: -0.0000

Data Index: 1376917 (The Pile)

Max Activating Token Index: 998

Text #6

Max Range: 1.1697. Min Range: -1.1697

Max Act: 0.8936. Min Act: -0.0000

Data Index: 168294 (The Pile)

Max Activating Token Index: 674

Text #7

Max Range: 1.1697. Min Range: -1.1697

Max Act: 0.9232. Min Act: -0.0000

Data Index: 465049 (The Pile)

Max Activating Token Index: 714

Text #8

Max Range: 1.1697. Min Range: -1.1697

Max Act: 0.8226. Min Act: -0.0000

Data Index: 1055210 (The Pile)

Max Activating Token Index: 306

Text #9

Max Range: 1.1697. Min Range: -1.1697

Max Act: 0.8278. Min Act: -0.0000

Data Index: 1184063 (The Pile)

Max Activating Token Index: 378

Text #10

Max Range: 1.1697. Min Range: -1.1697

Max Act: 0.8811. Min Act: -0.0000

Data Index: 1729613 (The Pile)

Max Activating Token Index: 920

Text #11

Max Range: 1.1697. Min Range: -1.1697

Max Act: 0.8166. Min Act: -0.0000

Data Index: 17721 (The Pile)

Max Activating Token Index: 754

Text #12

Max Range: 1.1697. Min Range: -1.1697

Max Act: 0.8466. Min Act: -0.0000

Data Index: 485182 (The Pile)

Max Activating Token Index: 902

Text #13

Max Range: 1.1697. Min Range: -1.1697

Max Act: 0.8324. Min Act: -0.0000

Data Index: 1110986 (The Pile)

Max Activating Token Index: 171

Text #14

Max Range: 1.1697. Min Range: -1.1697

Max Act: 0.8391. Min Act: -0.0000

Data Index: 1095167 (The Pile)

Max Activating Token Index: 219

Text #15

Max Range: 1.1697. Min Range: -1.1697

Max Act: 0.7947. Min Act: -0.0000

Data Index: 515017 (The Pile)

Max Activating Token Index: 306

Text #16

Max Range: 1.1697. Min Range: -1.1697

Max Act: 0.7971. Min Act: -0.0000

Data Index: 341016 (The Pile)

Max Activating Token Index: 423

Text #17

Max Range: 1.1697. Min Range: -1.1697

Max Act: 0.8650. Min Act: -0.0000

Data Index: 1785010 (The Pile)

Max Activating Token Index: 704

Text #18

Max Range: 1.1697. Min Range: -1.1697

Max Act: 0.7492. Min Act: -0.0000

Data Index: 590953 (The Pile)

Max Activating Token Index: 889

Text #19

Max Range: 1.1697. Min Range: -1.1697

Max Act: 0.7993. Min Act: -0.0000

Data Index: 1562059 (The Pile)

Max Activating Token Index: 734