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

Dataset: The Pile

Neuron 4382 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: 3.8704. Min Range: -3.8704

Max Act: 3.5276. Min Act: -0.0000

Data Index: 967755 (The Pile)

Max Activating Token Index: 1012

Text #1

Max Range: 3.8704. Min Range: -3.8704

Max Act: 3.1633. Min Act: -0.0000

Data Index: 1650691 (The Pile)

Max Activating Token Index: 822

Text #2

Max Range: 3.8704. Min Range: -3.8704

Max Act: 3.8704. Min Act: -0.0000

Data Index: 1099227 (The Pile)

Max Activating Token Index: 607

Text #3

Max Range: 3.8704. Min Range: -3.8704

Max Act: 3.7692. Min Act: -0.0000

Data Index: 552904 (The Pile)

Max Activating Token Index: 706

Text #4

Max Range: 3.8704. Min Range: -3.8704

Max Act: 3.7370. Min Act: -0.0000

Data Index: 124766 (The Pile)

Max Activating Token Index: 735

Text #5

Max Range: 3.8704. Min Range: -3.8704

Max Act: 3.3013. Min Act: -0.0000

Data Index: 415651 (The Pile)

Max Activating Token Index: 283

Text #6

Max Range: 3.8704. Min Range: -3.8704

Max Act: 3.3918. Min Act: -0.0000

Data Index: 133024 (The Pile)

Max Activating Token Index: 443

Text #7

Max Range: 3.8704. Min Range: -3.8704

Max Act: 3.1831. Min Act: -0.0000

Data Index: 417035 (The Pile)

Max Activating Token Index: 670

Text #8

Max Range: 3.8704. Min Range: -3.8704

Max Act: 3.2735. Min Act: -0.0000

Data Index: 1618072 (The Pile)

Max Activating Token Index: 942

Text #9

Max Range: 3.8704. Min Range: -3.8704

Max Act: 3.1174. Min Act: -0.0000

Data Index: 1298526 (The Pile)

Max Activating Token Index: 985

Text #10

Max Range: 3.8704. Min Range: -3.8704

Max Act: 3.4550. Min Act: -0.0000

Data Index: 134177 (The Pile)

Max Activating Token Index: 976

Text #11

Max Range: 3.8704. Min Range: -3.8704

Max Act: 3.1553. Min Act: -0.0000

Data Index: 1904200 (The Pile)

Max Activating Token Index: 1008

Text #12

Max Range: 3.8704. Min Range: -3.8704

Max Act: 2.9987. Min Act: -0.0000

Data Index: 207965 (The Pile)

Max Activating Token Index: 684

Text #13

Max Range: 3.8704. Min Range: -3.8704

Max Act: 3.4715. Min Act: -0.0000

Data Index: 1098790 (The Pile)

Max Activating Token Index: 623

Text #14

Max Range: 3.8704. Min Range: -3.8704

Max Act: 3.0560. Min Act: -0.0000

Data Index: 413866 (The Pile)

Max Activating Token Index: 499

Text #15

Max Range: 3.8704. Min Range: -3.8704

Max Act: 3.2972. Min Act: -0.0000

Data Index: 1256796 (The Pile)

Max Activating Token Index: 913

Text #16

Max Range: 3.8704. Min Range: -3.8704

Max Act: 2.8135. Min Act: -0.0000

Data Index: 1042566 (The Pile)

Max Activating Token Index: 604

Text #17

Max Range: 3.8704. Min Range: -3.8704

Max Act: 3.1167. Min Act: -0.0000

Data Index: 1131522 (The Pile)

Max Activating Token Index: 419

Text #18

Max Range: 3.8704. Min Range: -3.8704

Max Act: 3.0976. Min Act: -0.0000

Data Index: 1256139 (The Pile)

Max Activating Token Index: 575

Text #19

Max Range: 3.8704. Min Range: -3.8704

Max Act: 2.9755. Min Act: -0.0000

Data Index: 221228 (The Pile)

Max Activating Token Index: 861