Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 1282 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.0862. Min Range: -1.0862

Max Act: 1.0688. Min Act: -0.0000

Data Index: 1798839 (The Pile)

Max Activating Token Index: 996

Text #1

Max Range: 1.0862. Min Range: -1.0862

Max Act: 1.0820. Min Act: -0.0000

Data Index: 138798 (The Pile)

Max Activating Token Index: 875

Text #2

Max Range: 1.0862. Min Range: -1.0862

Max Act: 1.0862. Min Act: -0.0000

Data Index: 266564 (The Pile)

Max Activating Token Index: 868

Text #3

Max Range: 1.0862. Min Range: -1.0862

Max Act: 0.9454. Min Act: -0.0000

Data Index: 632597 (The Pile)

Max Activating Token Index: 650

Text #4

Max Range: 1.0862. Min Range: -1.0862

Max Act: 1.0193. Min Act: -0.0000

Data Index: 1070162 (The Pile)

Max Activating Token Index: 129

Text #5

Max Range: 1.0862. Min Range: -1.0862

Max Act: 1.0386. Min Act: -0.0000

Data Index: 344808 (The Pile)

Max Activating Token Index: 236

Text #6

Max Range: 1.0862. Min Range: -1.0862

Max Act: 1.0058. Min Act: -0.0000

Data Index: 953443 (The Pile)

Max Activating Token Index: 332

Text #7

Max Range: 1.0862. Min Range: -1.0862

Max Act: 1.0370. Min Act: 0.0000

Data Index: 1813597 (The Pile)

Max Activating Token Index: 742

Text #8

Max Range: 1.0862. Min Range: -1.0862

Max Act: 1.0401. Min Act: 0.0000

Data Index: 1997542 (The Pile)

Max Activating Token Index: 980

Text #9

Max Range: 1.0862. Min Range: -1.0862

Max Act: 0.9140. Min Act: 0.0000

Data Index: 611483 (The Pile)

Max Activating Token Index: 899

Text #10

Max Range: 1.0862. Min Range: -1.0862

Max Act: 1.0017. Min Act: 0.0000

Data Index: 1328654 (The Pile)

Max Activating Token Index: 532

Text #11

Max Range: 1.0862. Min Range: -1.0862

Max Act: 1.0101. Min Act: -0.0000

Data Index: 295123 (The Pile)

Max Activating Token Index: 209

Text #12

Max Range: 1.0862. Min Range: -1.0862

Max Act: 1.0279. Min Act: -0.0000

Data Index: 889636 (The Pile)

Max Activating Token Index: 728

Text #13

Max Range: 1.0862. Min Range: -1.0862

Max Act: 1.0517. Min Act: -0.0000

Data Index: 271747 (The Pile)

Max Activating Token Index: 965

Text #14

Max Range: 1.0862. Min Range: -1.0862

Max Act: 0.9620. Min Act: -0.0000

Data Index: 1670907 (The Pile)

Max Activating Token Index: 785

Text #15

Max Range: 1.0862. Min Range: -1.0862

Max Act: 1.0428. Min Act: -0.0000

Data Index: 207117 (The Pile)

Max Activating Token Index: 893

Text #16

Max Range: 1.0862. Min Range: -1.0862

Max Act: 0.9660. Min Act: -0.0000

Data Index: 1788689 (The Pile)

Max Activating Token Index: 904

Text #17

Max Range: 1.0862. Min Range: -1.0862

Max Act: 0.9668. Min Act: -0.0000

Data Index: 1730680 (The Pile)

Max Activating Token Index: 216

Text #18

Max Range: 1.0862. Min Range: -1.0862

Max Act: 0.9850. Min Act: -0.0000

Data Index: 502958 (The Pile)

Max Activating Token Index: 301

Text #19

Max Range: 1.0862. Min Range: -1.0862

Max Act: 0.9082. Min Act: -0.0000

Data Index: 1678161 (The Pile)

Max Activating Token Index: 419