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

Dataset: The Pile

Neuron 3663 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: 1.5449. Min Range: -1.5449

Max Act: 1.5449. Min Act: 0.0000

Data Index: 1537073 (The Pile)

Max Activating Token Index: 282

Text #1

Max Range: 1.5449. Min Range: -1.5449

Max Act: 1.4749. Min Act: -0.0000

Data Index: 930771 (The Pile)

Max Activating Token Index: 293

Text #2

Max Range: 1.5449. Min Range: -1.5449

Max Act: 1.2998. Min Act: -0.0000

Data Index: 1798365 (The Pile)

Max Activating Token Index: 447

Text #3

Max Range: 1.5449. Min Range: -1.5449

Max Act: 1.2866. Min Act: -0.0000

Data Index: 746317 (The Pile)

Max Activating Token Index: 348

Text #4

Max Range: 1.5449. Min Range: -1.5449

Max Act: 1.3618. Min Act: -0.0000

Data Index: 1926985 (The Pile)

Max Activating Token Index: 787

Text #5

Max Range: 1.5449. Min Range: -1.5449

Max Act: 1.2583. Min Act: -0.0000

Data Index: 1364885 (The Pile)

Max Activating Token Index: 1023

Text #6

Max Range: 1.5449. Min Range: -1.5449

Max Act: 1.1903. Min Act: -0.0000

Data Index: 1501979 (The Pile)

Max Activating Token Index: 599

Text #7

Max Range: 1.5449. Min Range: -1.5449

Max Act: 1.1260. Min Act: -0.0000

Data Index: 1543732 (The Pile)

Max Activating Token Index: 866

Text #8

Max Range: 1.5449. Min Range: -1.5449

Max Act: 1.2001. Min Act: -0.0000

Data Index: 1145416 (The Pile)

Max Activating Token Index: 165

Text #9

Max Range: 1.5449. Min Range: -1.5449

Max Act: 1.1857. Min Act: -0.0000

Data Index: 19672 (The Pile)

Max Activating Token Index: 903

Text #10

Max Range: 1.5449. Min Range: -1.5449

Max Act: 1.1830. Min Act: -0.0000

Data Index: 1558805 (The Pile)

Max Activating Token Index: 1016

Text #11

Max Range: 1.5449. Min Range: -1.5449

Max Act: 1.1658. Min Act: -0.0000

Data Index: 956488 (The Pile)

Max Activating Token Index: 868

Text #12

Max Range: 1.5449. Min Range: -1.5449

Max Act: 1.1364. Min Act: -0.0000

Data Index: 1806805 (The Pile)

Max Activating Token Index: 214

Text #13

Max Range: 1.5449. Min Range: -1.5449

Max Act: 1.1987. Min Act: -0.0000

Data Index: 656738 (The Pile)

Max Activating Token Index: 754

Text #14

Max Range: 1.5449. Min Range: -1.5449

Max Act: 1.1892. Min Act: -0.0000

Data Index: 626316 (The Pile)

Max Activating Token Index: 22

Text #15

Max Range: 1.5449. Min Range: -1.5449

Max Act: 1.1057. Min Act: -0.0000

Data Index: 1770584 (The Pile)

Max Activating Token Index: 586

Text #16

Max Range: 1.5449. Min Range: -1.5449

Max Act: 1.1804. Min Act: -0.0000

Data Index: 62763 (The Pile)

Max Activating Token Index: 1016

Text #17

Max Range: 1.5449. Min Range: -1.5449

Max Act: 1.0954. Min Act: 0.0000

Data Index: 1345187 (The Pile)

Max Activating Token Index: 342

Text #18

Max Range: 1.5449. Min Range: -1.5449

Max Act: 1.0922. Min Act: -0.0000

Data Index: 576032 (The Pile)

Max Activating Token Index: 658

Text #19

Max Range: 1.5449. Min Range: -1.5449

Max Act: 1.0960. Min Act: -0.0000

Data Index: 18740 (The Pile)

Max Activating Token Index: 317