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

Dataset: The Pile

Neuron 1152 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: 3.6043. Min Range: -3.6043

Max Act: 3.6043. Min Act: -0.0000

Data Index: 1529657 (The Pile)

Max Activating Token Index: 940

Text #1

Max Range: 3.6043. Min Range: -3.6043

Max Act: 3.0823. Min Act: -0.0000

Data Index: 823609 (The Pile)

Max Activating Token Index: 840

Text #2

Max Range: 3.6043. Min Range: -3.6043

Max Act: 3.0020. Min Act: -0.0000

Data Index: 77253 (The Pile)

Max Activating Token Index: 808

Text #3

Max Range: 3.6043. Min Range: -3.6043

Max Act: 2.7729. Min Act: -0.0000

Data Index: 1648760 (The Pile)

Max Activating Token Index: 788

Text #4

Max Range: 3.6043. Min Range: -3.6043

Max Act: 2.7443. Min Act: -0.0000

Data Index: 55230 (The Pile)

Max Activating Token Index: 690

Text #5

Max Range: 3.6043. Min Range: -3.6043

Max Act: 2.7259. Min Act: -0.0000

Data Index: 393078 (The Pile)

Max Activating Token Index: 742

Text #6

Max Range: 3.6043. Min Range: -3.6043

Max Act: 2.6798. Min Act: -0.0000

Data Index: 728962 (The Pile)

Max Activating Token Index: 573

Text #7

Max Range: 3.6043. Min Range: -3.6043

Max Act: 2.6480. Min Act: -0.0000

Data Index: 1091611 (The Pile)

Max Activating Token Index: 393

Text #8

Max Range: 3.6043. Min Range: -3.6043

Max Act: 2.7357. Min Act: -0.0000

Data Index: 1905468 (The Pile)

Max Activating Token Index: 703

Text #9

Max Range: 3.6043. Min Range: -3.6043

Max Act: 2.7504. Min Act: -0.0000

Data Index: 1306806 (The Pile)

Max Activating Token Index: 604

Text #10

Max Range: 3.6043. Min Range: -3.6043

Max Act: 2.5590. Min Act: -0.0000

Data Index: 70576 (The Pile)

Max Activating Token Index: 766

Text #11

Max Range: 3.6043. Min Range: -3.6043

Max Act: 2.4277. Min Act: -0.0000

Data Index: 1585073 (The Pile)

Max Activating Token Index: 251

Text #12

Max Range: 3.6043. Min Range: -3.6043

Max Act: 2.5500. Min Act: -0.0000

Data Index: 141921 (The Pile)

Max Activating Token Index: 438

Text #13

Max Range: 3.6043. Min Range: -3.6043

Max Act: 2.5493. Min Act: -0.0000

Data Index: 148551 (The Pile)

Max Activating Token Index: 574

Text #14

Max Range: 3.6043. Min Range: -3.6043

Max Act: 2.6552. Min Act: -0.0000

Data Index: 1777075 (The Pile)

Max Activating Token Index: 936

Text #15

Max Range: 3.6043. Min Range: -3.6043

Max Act: 2.5373. Min Act: -0.0000

Data Index: 1840934 (The Pile)

Max Activating Token Index: 499

Text #16

Max Range: 3.6043. Min Range: -3.6043

Max Act: 2.4048. Min Act: -0.0000

Data Index: 1913576 (The Pile)

Max Activating Token Index: 473

Text #17

Max Range: 3.6043. Min Range: -3.6043

Max Act: 2.5077. Min Act: -0.0000

Data Index: 1033922 (The Pile)

Max Activating Token Index: 456

Text #18

Max Range: 3.6043. Min Range: -3.6043

Max Act: 2.5030. Min Act: -0.0000

Data Index: 1955936 (The Pile)

Max Activating Token Index: 452

Text #19

Max Range: 3.6043. Min Range: -3.6043

Max Act: 2.5104. Min Act: -0.0000

Data Index: 231014 (The Pile)

Max Activating Token Index: 975