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

Dataset: The Pile

Neuron 3598 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: 1.7312. Min Range: -1.7312

Max Act: 1.7312. Min Act: -0.0000

Data Index: 162795 (The Pile)

Max Activating Token Index: 638

Text #1

Max Range: 1.7312. Min Range: -1.7312

Max Act: 1.3192. Min Act: -0.0000

Data Index: 1565839 (The Pile)

Max Activating Token Index: 734

Text #2

Max Range: 1.7312. Min Range: -1.7312

Max Act: 1.4690. Min Act: -0.0000

Data Index: 663638 (The Pile)

Max Activating Token Index: 748

Text #3

Max Range: 1.7312. Min Range: -1.7312

Max Act: 1.1449. Min Act: -0.0000

Data Index: 575735 (The Pile)

Max Activating Token Index: 225

Text #4

Max Range: 1.7312. Min Range: -1.7312

Max Act: 1.1114. Min Act: -0.0000

Data Index: 354527 (The Pile)

Max Activating Token Index: 451

Text #5

Max Range: 1.7312. Min Range: -1.7312

Max Act: 1.0502. Min Act: -0.0000

Data Index: 594890 (The Pile)

Max Activating Token Index: 706

Text #6

Max Range: 1.7312. Min Range: -1.7312

Max Act: 1.0226. Min Act: -0.0000

Data Index: 49092 (The Pile)

Max Activating Token Index: 684

Text #7

Max Range: 1.7312. Min Range: -1.7312

Max Act: 0.9170. Min Act: -0.0000

Data Index: 1472851 (The Pile)

Max Activating Token Index: 147

Text #8

Max Range: 1.7312. Min Range: -1.7312

Max Act: 0.9830. Min Act: -0.0000

Data Index: 1932471 (The Pile)

Max Activating Token Index: 446

Text #9

Max Range: 1.7312. Min Range: -1.7312

Max Act: 0.8633. Min Act: -0.0000

Data Index: 1123903 (The Pile)

Max Activating Token Index: 728

Text #10

Max Range: 1.7312. Min Range: -1.7312

Max Act: 0.9561. Min Act: -0.0000

Data Index: 1063194 (The Pile)

Max Activating Token Index: 652

Text #11

Max Range: 1.7312. Min Range: -1.7312

Max Act: 0.9759. Min Act: -0.0000

Data Index: 150546 (The Pile)

Max Activating Token Index: 818

Text #12

Max Range: 1.7312. Min Range: -1.7312

Max Act: 0.8847. Min Act: -0.0000

Data Index: 1397005 (The Pile)

Max Activating Token Index: 644

Text #13

Max Range: 1.7312. Min Range: -1.7312

Max Act: 0.7914. Min Act: -0.0000

Data Index: 1727269 (The Pile)

Max Activating Token Index: 566

Text #14

Max Range: 1.7312. Min Range: -1.7312

Max Act: 0.8368. Min Act: 0.0000

Data Index: 1012222 (The Pile)

Max Activating Token Index: 13

Text #15

Max Range: 1.7312. Min Range: -1.7312

Max Act: 0.8100. Min Act: -0.0000

Data Index: 1770855 (The Pile)

Max Activating Token Index: 381

Text #16

Max Range: 1.7312. Min Range: -1.7312

Max Act: 0.8448. Min Act: -0.0000

Data Index: 1826457 (The Pile)

Max Activating Token Index: 610

Text #17

Max Range: 1.7312. Min Range: -1.7312

Max Act: 0.7124. Min Act: -0.0000

Data Index: 1989553 (The Pile)

Max Activating Token Index: 706

Text #18

Max Range: 1.7312. Min Range: -1.7312

Max Act: 0.7618. Min Act: -0.0000

Data Index: 1098398 (The Pile)

Max Activating Token Index: 329

Text #19

Max Range: 1.7312. Min Range: -1.7312

Max Act: 0.7999. Min Act: -0.0000

Data Index: 884220 (The Pile)

Max Activating Token Index: 351