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

Dataset: The Pile

Neuron 2622 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: 0.5316. Min Range: -0.5316

Max Act: 0.5316. Min Act: -0.0000

Data Index: 417340 (The Pile)

Max Activating Token Index: 37

Text #1

Max Range: 0.5316. Min Range: -0.5316

Max Act: 0.4245. Min Act: -0.0000

Data Index: 919797 (The Pile)

Max Activating Token Index: 218

Text #2

Max Range: 0.5316. Min Range: -0.5316

Max Act: 0.3816. Min Act: -0.0000

Data Index: 226312 (The Pile)

Max Activating Token Index: 803

Text #3

Max Range: 0.5316. Min Range: -0.5316

Max Act: 0.3695. Min Act: -0.0000

Data Index: 1110523 (The Pile)

Max Activating Token Index: 388

Text #4

Max Range: 0.5316. Min Range: -0.5316

Max Act: 0.3753. Min Act: -0.0000

Data Index: 1947314 (The Pile)

Max Activating Token Index: 433

Text #5

Max Range: 0.5316. Min Range: -0.5316

Max Act: 0.3950. Min Act: -0.0000

Data Index: 390331 (The Pile)

Max Activating Token Index: 953

Text #6

Max Range: 0.5316. Min Range: -0.5316

Max Act: 0.3712. Min Act: -0.0000

Data Index: 1200556 (The Pile)

Max Activating Token Index: 251

Text #7

Max Range: 0.5316. Min Range: -0.5316

Max Act: 0.3549. Min Act: -0.0000

Data Index: 986437 (The Pile)

Max Activating Token Index: 1001

Text #8

Max Range: 0.5316. Min Range: -0.5316

Max Act: 0.3563. Min Act: -0.0000

Data Index: 1561655 (The Pile)

Max Activating Token Index: 213

Text #9

Max Range: 0.5316. Min Range: -0.5316

Max Act: 0.3426. Min Act: -0.0000

Data Index: 422869 (The Pile)

Max Activating Token Index: 619

Text #10

Max Range: 0.5316. Min Range: -0.5316

Max Act: 0.3175. Min Act: -0.0000

Data Index: 1088817 (The Pile)

Max Activating Token Index: 595

Text #11

Max Range: 0.5316. Min Range: -0.5316

Max Act: 0.3374. Min Act: -0.0000

Data Index: 1130751 (The Pile)

Max Activating Token Index: 788

Text #12

Max Range: 0.5316. Min Range: -0.5316

Max Act: 0.3663. Min Act: -0.0000

Data Index: 216706 (The Pile)

Max Activating Token Index: 668

Text #13

Max Range: 0.5316. Min Range: -0.5316

Max Act: 0.3307. Min Act: -0.0000

Data Index: 222368 (The Pile)

Max Activating Token Index: 25

Text #14

Max Range: 0.5316. Min Range: -0.5316

Max Act: 0.3313. Min Act: -0.0000

Data Index: 39781 (The Pile)

Max Activating Token Index: 1013

Text #15

Max Range: 0.5316. Min Range: -0.5316

Max Act: 0.3406. Min Act: -0.0000

Data Index: 465998 (The Pile)

Max Activating Token Index: 1022

Text #16

Max Range: 0.5316. Min Range: -0.5316

Max Act: 0.3116. Min Act: -0.0000

Data Index: 168900 (The Pile)

Max Activating Token Index: 1012

Text #17

Max Range: 0.5316. Min Range: -0.5316

Max Act: 0.2979. Min Act: -0.0000

Data Index: 654353 (The Pile)

Max Activating Token Index: 689

Text #18

Max Range: 0.5316. Min Range: -0.5316

Max Act: 0.3570. Min Act: -0.0000

Data Index: 748434 (The Pile)

Max Activating Token Index: 775

Text #19

Max Range: 0.5316. Min Range: -0.5316

Max Act: 0.3090. Min Act: -0.0000

Data Index: 757079 (The Pile)

Max Activating Token Index: 261