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

Dataset: The Pile

Neuron 2246 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: 1.1812. Min Range: -1.1812

Max Act: 1.1812. Min Act: -0.0000

Data Index: 242931 (The Pile)

Max Activating Token Index: 241

Text #1

Max Range: 1.1812. Min Range: -1.1812

Max Act: 1.1094. Min Act: -0.0000

Data Index: 1734030 (The Pile)

Max Activating Token Index: 498

Text #2

Max Range: 1.1812. Min Range: -1.1812

Max Act: 1.0675. Min Act: -0.0000

Data Index: 1969340 (The Pile)

Max Activating Token Index: 777

Text #3

Max Range: 1.1812. Min Range: -1.1812

Max Act: 0.9211. Min Act: -0.0000

Data Index: 1334686 (The Pile)

Max Activating Token Index: 612

Text #4

Max Range: 1.1812. Min Range: -1.1812

Max Act: 0.9117. Min Act: -0.0000

Data Index: 1825870 (The Pile)

Max Activating Token Index: 623

Text #5

Max Range: 1.1812. Min Range: -1.1812

Max Act: 0.8599. Min Act: -0.0000

Data Index: 600627 (The Pile)

Max Activating Token Index: 108

Text #6

Max Range: 1.1812. Min Range: -1.1812

Max Act: 0.7984. Min Act: -0.0000

Data Index: 433271 (The Pile)

Max Activating Token Index: 677

Text #7

Max Range: 1.1812. Min Range: -1.1812

Max Act: 0.8328. Min Act: -0.0000

Data Index: 1552390 (The Pile)

Max Activating Token Index: 120

Text #8

Max Range: 1.1812. Min Range: -1.1812

Max Act: 0.7485. Min Act: -0.0000

Data Index: 1561902 (The Pile)

Max Activating Token Index: 951

Text #9

Max Range: 1.1812. Min Range: -1.1812

Max Act: 0.7673. Min Act: -0.0000

Data Index: 1509022 (The Pile)

Max Activating Token Index: 468

Text #10

Max Range: 1.1812. Min Range: -1.1812

Max Act: 0.7380. Min Act: -0.0000

Data Index: 1630091 (The Pile)

Max Activating Token Index: 108

Text #11

Max Range: 1.1812. Min Range: -1.1812

Max Act: 0.7389. Min Act: -0.0000

Data Index: 1183721 (The Pile)

Max Activating Token Index: 836

Text #12

Max Range: 1.1812. Min Range: -1.1812

Max Act: 0.7063. Min Act: -0.0000

Data Index: 1988150 (The Pile)

Max Activating Token Index: 634

Text #13

Max Range: 1.1812. Min Range: -1.1812

Max Act: 0.7732. Min Act: -0.0000

Data Index: 1548834 (The Pile)

Max Activating Token Index: 1014

Text #14

Max Range: 1.1812. Min Range: -1.1812

Max Act: 0.6963. Min Act: -0.0000

Data Index: 1403892 (The Pile)

Max Activating Token Index: 499

Text #15

Max Range: 1.1812. Min Range: -1.1812

Max Act: 0.6217. Min Act: -0.0000

Data Index: 1609201 (The Pile)

Max Activating Token Index: 1002

Text #16

Max Range: 1.1812. Min Range: -1.1812

Max Act: 0.6759. Min Act: -0.0000

Data Index: 1677446 (The Pile)

Max Activating Token Index: 343

Text #17

Max Range: 1.1812. Min Range: -1.1812

Max Act: 0.6594. Min Act: -0.0000

Data Index: 1814911 (The Pile)

Max Activating Token Index: 373

Text #18

Max Range: 1.1812. Min Range: -1.1812

Max Act: 0.6297. Min Act: -0.0000

Data Index: 1958644 (The Pile)

Max Activating Token Index: 394

Text #19

Max Range: 1.1812. Min Range: -1.1812

Max Act: 0.6758. Min Act: -0.0000

Data Index: 456193 (The Pile)

Max Activating Token Index: 212