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

Dataset: The Pile

Neuron 299 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8688. Min Range: -0.8688

Max Act: 0.8688. Min Act: -0.0000

Data Index: 1999077 (The Pile)

Max Activating Token Index: 64

Text #1

Max Range: 0.8688. Min Range: -0.8688

Max Act: 0.7198. Min Act: -0.0000

Data Index: 828620 (The Pile)

Max Activating Token Index: 452

Text #2

Max Range: 0.8688. Min Range: -0.8688

Max Act: 0.6194. Min Act: -0.0000

Data Index: 417475 (The Pile)

Max Activating Token Index: 668

Text #3

Max Range: 0.8688. Min Range: -0.8688

Max Act: 0.6328. Min Act: -0.0000

Data Index: 643819 (The Pile)

Max Activating Token Index: 891

Text #4

Max Range: 0.8688. Min Range: -0.8688

Max Act: 0.5685. Min Act: -0.0000

Data Index: 29345 (The Pile)

Max Activating Token Index: 598

Text #5

Max Range: 0.8688. Min Range: -0.8688

Max Act: 0.5766. Min Act: -0.0000

Data Index: 1458291 (The Pile)

Max Activating Token Index: 51

Text #6

Max Range: 0.8688. Min Range: -0.8688

Max Act: 0.5591. Min Act: -0.0000

Data Index: 1131157 (The Pile)

Max Activating Token Index: 441

Text #7

Max Range: 0.8688. Min Range: -0.8688

Max Act: 0.5730. Min Act: -0.0000

Data Index: 1603438 (The Pile)

Max Activating Token Index: 461

Text #8

Max Range: 0.8688. Min Range: -0.8688

Max Act: 0.5702. Min Act: -0.0000

Data Index: 1986126 (The Pile)

Max Activating Token Index: 290

Text #9

Max Range: 0.8688. Min Range: -0.8688

Max Act: 0.5427. Min Act: -0.0000

Data Index: 581077 (The Pile)

Max Activating Token Index: 170

Text #10

Max Range: 0.8688. Min Range: -0.8688

Max Act: 0.5490. Min Act: -0.0000

Data Index: 1425842 (The Pile)

Max Activating Token Index: 307

Text #11

Max Range: 0.8688. Min Range: -0.8688

Max Act: 0.5492. Min Act: -0.0000

Data Index: 454294 (The Pile)

Max Activating Token Index: 305

Text #12

Max Range: 0.8688. Min Range: -0.8688

Max Act: 0.5655. Min Act: -0.0000

Data Index: 1077687 (The Pile)

Max Activating Token Index: 459

Text #13

Max Range: 0.8688. Min Range: -0.8688

Max Act: 0.5314. Min Act: -0.0000

Data Index: 203561 (The Pile)

Max Activating Token Index: 769

Text #14

Max Range: 0.8688. Min Range: -0.8688

Max Act: 0.6082. Min Act: -0.0000

Data Index: 492022 (The Pile)

Max Activating Token Index: 955

Text #15

Max Range: 0.8688. Min Range: -0.8688

Max Act: 0.5173. Min Act: -0.0000

Data Index: 704970 (The Pile)

Max Activating Token Index: 406

Text #16

Max Range: 0.8688. Min Range: -0.8688

Max Act: 0.5500. Min Act: -0.0000

Data Index: 1572036 (The Pile)

Max Activating Token Index: 109

Text #17

Max Range: 0.8688. Min Range: -0.8688

Max Act: 0.5031. Min Act: -0.0000

Data Index: 854782 (The Pile)

Max Activating Token Index: 753

Text #18

Max Range: 0.8688. Min Range: -0.8688

Max Act: 0.5200. Min Act: -0.0000

Data Index: 1782374 (The Pile)

Max Activating Token Index: 747

Text #19

Max Range: 0.8688. Min Range: -0.8688

Max Act: 0.5479. Min Act: -0.0000

Data Index: 1834764 (The Pile)

Max Activating Token Index: 274