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

Dataset: The Pile

Neuron 3454 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: 0.5624. Min Range: -0.5624

Max Act: 0.5624. Min Act: -0.0000

Data Index: 979824 (The Pile)

Max Activating Token Index: 430

Text #1

Max Range: 0.5624. Min Range: -0.5624

Max Act: 0.5538. Min Act: -0.0000

Data Index: 888391 (The Pile)

Max Activating Token Index: 242

Text #2

Max Range: 0.5624. Min Range: -0.5624

Max Act: 0.5208. Min Act: -0.0000

Data Index: 1440054 (The Pile)

Max Activating Token Index: 426

Text #3

Max Range: 0.5624. Min Range: -0.5624

Max Act: 0.5170. Min Act: -0.0000

Data Index: 160558 (The Pile)

Max Activating Token Index: 239

Text #4

Max Range: 0.5624. Min Range: -0.5624

Max Act: 0.4751. Min Act: -0.0000

Data Index: 1619393 (The Pile)

Max Activating Token Index: 505

Text #5

Max Range: 0.5624. Min Range: -0.5624

Max Act: 0.4907. Min Act: -0.0000

Data Index: 1261706 (The Pile)

Max Activating Token Index: 825

Text #6

Max Range: 0.5624. Min Range: -0.5624

Max Act: 0.4837. Min Act: -0.0000

Data Index: 1172241 (The Pile)

Max Activating Token Index: 888

Text #7

Max Range: 0.5624. Min Range: -0.5624

Max Act: 0.4820. Min Act: -0.0000

Data Index: 1380727 (The Pile)

Max Activating Token Index: 659

Text #8

Max Range: 0.5624. Min Range: -0.5624

Max Act: 0.4781. Min Act: -0.0000

Data Index: 1472962 (The Pile)

Max Activating Token Index: 581

Text #9

Max Range: 0.5624. Min Range: -0.5624

Max Act: 0.4789. Min Act: -0.0000

Data Index: 295467 (The Pile)

Max Activating Token Index: 573

Text #10

Max Range: 0.5624. Min Range: -0.5624

Max Act: 0.4592. Min Act: -0.0000

Data Index: 1892940 (The Pile)

Max Activating Token Index: 355

Text #11

Max Range: 0.5624. Min Range: -0.5624

Max Act: 0.4551. Min Act: -0.0000

Data Index: 953040 (The Pile)

Max Activating Token Index: 552

Text #12

Max Range: 0.5624. Min Range: -0.5624

Max Act: 0.4636. Min Act: -0.0000

Data Index: 743636 (The Pile)

Max Activating Token Index: 731

Text #13

Max Range: 0.5624. Min Range: -0.5624

Max Act: 0.4301. Min Act: -0.0000

Data Index: 304749 (The Pile)

Max Activating Token Index: 66

Text #14

Max Range: 0.5624. Min Range: -0.5624

Max Act: 0.4465. Min Act: -0.0000

Data Index: 603884 (The Pile)

Max Activating Token Index: 365

Text #15

Max Range: 0.5624. Min Range: -0.5624

Max Act: 0.4596. Min Act: -0.0000

Data Index: 34695 (The Pile)

Max Activating Token Index: 1023

Text #16

Max Range: 0.5624. Min Range: -0.5624

Max Act: 0.4476. Min Act: -0.0000

Data Index: 1896496 (The Pile)

Max Activating Token Index: 700

Text #17

Max Range: 0.5624. Min Range: -0.5624

Max Act: 0.4339. Min Act: -0.0000

Data Index: 766872 (The Pile)

Max Activating Token Index: 370

Text #18

Max Range: 0.5624. Min Range: -0.5624

Max Act: 0.4462. Min Act: -0.0000

Data Index: 88001 (The Pile)

Max Activating Token Index: 295

Text #19

Max Range: 0.5624. Min Range: -0.5624

Max Act: 0.4097. Min Act: -0.0000

Data Index: 734684 (The Pile)

Max Activating Token Index: 564