Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 2594 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.0517. Min Range: -1.0517

Max Act: 1.0517. Min Act: -0.0000

Data Index: 1659530 (The Pile)

Max Activating Token Index: 467

Text #1

Max Range: 1.0517. Min Range: -1.0517

Max Act: 0.9941. Min Act: -0.0000

Data Index: 327874 (The Pile)

Max Activating Token Index: 185

Text #2

Max Range: 1.0517. Min Range: -1.0517

Max Act: 0.9672. Min Act: -0.0000

Data Index: 1504431 (The Pile)

Max Activating Token Index: 163

Text #3

Max Range: 1.0517. Min Range: -1.0517

Max Act: 0.9201. Min Act: -0.0000

Data Index: 590468 (The Pile)

Max Activating Token Index: 48

Text #4

Max Range: 1.0517. Min Range: -1.0517

Max Act: 0.9494. Min Act: -0.0000

Data Index: 1177173 (The Pile)

Max Activating Token Index: 818

Text #5

Max Range: 1.0517. Min Range: -1.0517

Max Act: 0.9708. Min Act: -0.0000

Data Index: 924453 (The Pile)

Max Activating Token Index: 634

Text #6

Max Range: 1.0517. Min Range: -1.0517

Max Act: 0.9504. Min Act: -0.0000

Data Index: 529160 (The Pile)

Max Activating Token Index: 272

Text #7

Max Range: 1.0517. Min Range: -1.0517

Max Act: 0.8910. Min Act: -0.0000

Data Index: 1646461 (The Pile)

Max Activating Token Index: 578

Text #8

Max Range: 1.0517. Min Range: -1.0517

Max Act: 0.9299. Min Act: -0.0000

Data Index: 614681 (The Pile)

Max Activating Token Index: 221

Text #9

Max Range: 1.0517. Min Range: -1.0517

Max Act: 0.9079. Min Act: -0.0000

Data Index: 1417362 (The Pile)

Max Activating Token Index: 733

Text #10

Max Range: 1.0517. Min Range: -1.0517

Max Act: 0.9051. Min Act: -0.0000

Data Index: 518677 (The Pile)

Max Activating Token Index: 346

Text #11

Max Range: 1.0517. Min Range: -1.0517

Max Act: 0.8817. Min Act: -0.0000

Data Index: 300932 (The Pile)

Max Activating Token Index: 601

Text #12

Max Range: 1.0517. Min Range: -1.0517

Max Act: 0.8979. Min Act: -0.0000

Data Index: 424795 (The Pile)

Max Activating Token Index: 119

Text #13

Max Range: 1.0517. Min Range: -1.0517

Max Act: 0.8454. Min Act: -0.0000

Data Index: 140370 (The Pile)

Max Activating Token Index: 281

Text #14

Max Range: 1.0517. Min Range: -1.0517

Max Act: 0.8707. Min Act: -0.0000

Data Index: 1960056 (The Pile)

Max Activating Token Index: 1019

Text #15

Max Range: 1.0517. Min Range: -1.0517

Max Act: 0.8566. Min Act: -0.0000

Data Index: 1932173 (The Pile)

Max Activating Token Index: 465

Text #16

Max Range: 1.0517. Min Range: -1.0517

Max Act: 0.8574. Min Act: -0.0000

Data Index: 1540427 (The Pile)

Max Activating Token Index: 406

Text #17

Max Range: 1.0517. Min Range: -1.0517

Max Act: 0.8629. Min Act: -0.0000

Data Index: 961547 (The Pile)

Max Activating Token Index: 63

Text #18

Max Range: 1.0517. Min Range: -1.0517

Max Act: 0.8074. Min Act: -0.0000

Data Index: 1547562 (The Pile)

Max Activating Token Index: 396

Text #19

Max Range: 1.0517. Min Range: -1.0517

Max Act: 0.8712. Min Act: -0.0000

Data Index: 1117518 (The Pile)

Max Activating Token Index: 17