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

Dataset: The Pile

Neuron 1751 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: 5.7746. Min Range: -5.7746

Max Act: 5.7746. Min Act: -0.0000

Data Index: 778962 (The Pile)

Max Activating Token Index: 187

Text #1

Max Range: 5.7746. Min Range: -5.7746

Max Act: 4.7733. Min Act: -0.0000

Data Index: 1357688 (The Pile)

Max Activating Token Index: 1009

Text #2

Max Range: 5.7746. Min Range: -5.7746

Max Act: 4.8648. Min Act: -0.0000

Data Index: 1201929 (The Pile)

Max Activating Token Index: 528

Text #3

Max Range: 5.7746. Min Range: -5.7746

Max Act: 4.7983. Min Act: -0.0000

Data Index: 527355 (The Pile)

Max Activating Token Index: 948

Text #4

Max Range: 5.7746. Min Range: -5.7746

Max Act: 4.7696. Min Act: -0.0000

Data Index: 1477817 (The Pile)

Max Activating Token Index: 894

Text #5

Max Range: 5.7746. Min Range: -5.7746

Max Act: 4.5879. Min Act: -0.0000

Data Index: 506284 (The Pile)

Max Activating Token Index: 385

Text #6

Max Range: 5.7746. Min Range: -5.7746

Max Act: 4.1292. Min Act: -0.0000

Data Index: 725492 (The Pile)

Max Activating Token Index: 451

Text #7

Max Range: 5.7746. Min Range: -5.7746

Max Act: 4.2993. Min Act: -0.0000

Data Index: 1860854 (The Pile)

Max Activating Token Index: 816

Text #8

Max Range: 5.7746. Min Range: -5.7746

Max Act: 4.2012. Min Act: -0.0000

Data Index: 1491457 (The Pile)

Max Activating Token Index: 724

Text #9

Max Range: 5.7746. Min Range: -5.7746

Max Act: 3.8202. Min Act: -0.0000

Data Index: 1982938 (The Pile)

Max Activating Token Index: 146

Text #10

Max Range: 5.7746. Min Range: -5.7746

Max Act: 3.9572. Min Act: -0.0000

Data Index: 931065 (The Pile)

Max Activating Token Index: 118

Text #11

Max Range: 5.7746. Min Range: -5.7746

Max Act: 3.9571. Min Act: -0.0000

Data Index: 520217 (The Pile)

Max Activating Token Index: 574

Text #12

Max Range: 5.7746. Min Range: -5.7746

Max Act: 3.9005. Min Act: -0.0000

Data Index: 1656796 (The Pile)

Max Activating Token Index: 375

Text #13

Max Range: 5.7746. Min Range: -5.7746

Max Act: 3.8592. Min Act: -0.0000

Data Index: 839440 (The Pile)

Max Activating Token Index: 260

Text #14

Max Range: 5.7746. Min Range: -5.7746

Max Act: 3.7876. Min Act: -0.0000

Data Index: 1010849 (The Pile)

Max Activating Token Index: 159

Text #15

Max Range: 5.7746. Min Range: -5.7746

Max Act: 3.6528. Min Act: -0.0000

Data Index: 1570769 (The Pile)

Max Activating Token Index: 688

Text #16

Max Range: 5.7746. Min Range: -5.7746

Max Act: 3.7009. Min Act: -0.0000

Data Index: 326915 (The Pile)

Max Activating Token Index: 931

Text #17

Max Range: 5.7746. Min Range: -5.7746

Max Act: 3.4576. Min Act: -0.0000

Data Index: 191648 (The Pile)

Max Activating Token Index: 831

Text #18

Max Range: 5.7746. Min Range: -5.7746

Max Act: 3.1829. Min Act: -0.0000

Data Index: 1696229 (The Pile)

Max Activating Token Index: 990

Text #19

Max Range: 5.7746. Min Range: -5.7746

Max Act: 3.1542. Min Act: -0.0000

Data Index: 101343 (The Pile)

Max Activating Token Index: 824