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

Dataset: The Pile

Neuron 3612 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 1.9556. Min Range: -1.9556

Max Act: 1.9556. Min Act: -0.0000

Data Index: 957419 (The Pile)

Max Activating Token Index: 332

Text #1

Max Range: 1.9556. Min Range: -1.9556

Max Act: 1.7563. Min Act: -0.0000

Data Index: 480873 (The Pile)

Max Activating Token Index: 638

Text #2

Max Range: 1.9556. Min Range: -1.9556

Max Act: 1.8630. Min Act: -0.0000

Data Index: 1751341 (The Pile)

Max Activating Token Index: 165

Text #3

Max Range: 1.9556. Min Range: -1.9556

Max Act: 1.7885. Min Act: -0.0000

Data Index: 1445451 (The Pile)

Max Activating Token Index: 107

Text #4

Max Range: 1.9556. Min Range: -1.9556

Max Act: 1.8403. Min Act: -0.0000

Data Index: 1302865 (The Pile)

Max Activating Token Index: 613

Text #5

Max Range: 1.9556. Min Range: -1.9556

Max Act: 1.6495. Min Act: -0.0000

Data Index: 1758782 (The Pile)

Max Activating Token Index: 172

Text #6

Max Range: 1.9556. Min Range: -1.9556

Max Act: 1.6456. Min Act: -0.0000

Data Index: 1238363 (The Pile)

Max Activating Token Index: 596

Text #7

Max Range: 1.9556. Min Range: -1.9556

Max Act: 1.7147. Min Act: -0.0000

Data Index: 818668 (The Pile)

Max Activating Token Index: 33

Text #8

Max Range: 1.9556. Min Range: -1.9556

Max Act: 1.6332. Min Act: -0.0000

Data Index: 219215 (The Pile)

Max Activating Token Index: 524

Text #9

Max Range: 1.9556. Min Range: -1.9556

Max Act: 1.7248. Min Act: -0.0000

Data Index: 433077 (The Pile)

Max Activating Token Index: 644

Text #10

Max Range: 1.9556. Min Range: -1.9556

Max Act: 1.7140. Min Act: -0.0000

Data Index: 1089105 (The Pile)

Max Activating Token Index: 203

Text #11

Max Range: 1.9556. Min Range: -1.9556

Max Act: 1.6887. Min Act: -0.0000

Data Index: 1431414 (The Pile)

Max Activating Token Index: 651

Text #12

Max Range: 1.9556. Min Range: -1.9556

Max Act: 1.6894. Min Act: -0.0000

Data Index: 1808743 (The Pile)

Max Activating Token Index: 528

Text #13

Max Range: 1.9556. Min Range: -1.9556

Max Act: 1.6853. Min Act: -0.0000

Data Index: 1809426 (The Pile)

Max Activating Token Index: 463

Text #14

Max Range: 1.9556. Min Range: -1.9556

Max Act: 1.6071. Min Act: -0.0000

Data Index: 1057735 (The Pile)

Max Activating Token Index: 588

Text #15

Max Range: 1.9556. Min Range: -1.9556

Max Act: 1.6665. Min Act: -0.0000

Data Index: 1203723 (The Pile)

Max Activating Token Index: 760

Text #16

Max Range: 1.9556. Min Range: -1.9556

Max Act: 1.5635. Min Act: -0.0000

Data Index: 247267 (The Pile)

Max Activating Token Index: 765

Text #17

Max Range: 1.9556. Min Range: -1.9556

Max Act: 1.6609. Min Act: -0.0000

Data Index: 1864493 (The Pile)

Max Activating Token Index: 921

Text #18

Max Range: 1.9556. Min Range: -1.9556

Max Act: 1.7544. Min Act: -0.0000

Data Index: 1217923 (The Pile)

Max Activating Token Index: 835

Text #19

Max Range: 1.9556. Min Range: -1.9556

Max Act: 1.6534. Min Act: -0.0000

Data Index: 915996 (The Pile)

Max Activating Token Index: 443