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

Dataset: The Pile

Neuron 554 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: 0.7502. Min Range: -0.7502

Max Act: 0.7502. Min Act: -0.0000

Data Index: 1380302 (The Pile)

Max Activating Token Index: 479

Text #1

Max Range: 0.7502. Min Range: -0.7502

Max Act: 0.6820. Min Act: -0.0000

Data Index: 1243958 (The Pile)

Max Activating Token Index: 869

Text #2

Max Range: 0.7502. Min Range: -0.7502

Max Act: 0.6535. Min Act: -0.0000

Data Index: 1792638 (The Pile)

Max Activating Token Index: 65

Text #3

Max Range: 0.7502. Min Range: -0.7502

Max Act: 0.6608. Min Act: -0.0000

Data Index: 597865 (The Pile)

Max Activating Token Index: 606

Text #4

Max Range: 0.7502. Min Range: -0.7502

Max Act: 0.5869. Min Act: -0.0000

Data Index: 1312998 (The Pile)

Max Activating Token Index: 494

Text #5

Max Range: 0.7502. Min Range: -0.7502

Max Act: 0.5667. Min Act: -0.0000

Data Index: 814765 (The Pile)

Max Activating Token Index: 483

Text #6

Max Range: 0.7502. Min Range: -0.7502

Max Act: 0.6030. Min Act: -0.0000

Data Index: 541270 (The Pile)

Max Activating Token Index: 227

Text #7

Max Range: 0.7502. Min Range: -0.7502

Max Act: 0.5758. Min Act: -0.0000

Data Index: 135610 (The Pile)

Max Activating Token Index: 864

Text #8

Max Range: 0.7502. Min Range: -0.7502

Max Act: 0.5735. Min Act: -0.0000

Data Index: 93976 (The Pile)

Max Activating Token Index: 352

Text #9

Max Range: 0.7502. Min Range: -0.7502

Max Act: 0.5726. Min Act: -0.0000

Data Index: 1874051 (The Pile)

Max Activating Token Index: 714

Text #10

Max Range: 0.7502. Min Range: -0.7502

Max Act: 0.5579. Min Act: -0.0000

Data Index: 720216 (The Pile)

Max Activating Token Index: 565

Text #11

Max Range: 0.7502. Min Range: -0.7502

Max Act: 0.5582. Min Act: -0.0000

Data Index: 767321 (The Pile)

Max Activating Token Index: 329

Text #12

Max Range: 0.7502. Min Range: -0.7502

Max Act: 0.5346. Min Act: -0.0000

Data Index: 1890985 (The Pile)

Max Activating Token Index: 451

Text #13

Max Range: 0.7502. Min Range: -0.7502

Max Act: 0.5454. Min Act: -0.0000

Data Index: 928069 (The Pile)

Max Activating Token Index: 57

Text #14

Max Range: 0.7502. Min Range: -0.7502

Max Act: 0.5129. Min Act: -0.0000

Data Index: 250641 (The Pile)

Max Activating Token Index: 704

Text #15

Max Range: 0.7502. Min Range: -0.7502

Max Act: 0.5150. Min Act: -0.0000

Data Index: 1457351 (The Pile)

Max Activating Token Index: 386

Text #16

Max Range: 0.7502. Min Range: -0.7502

Max Act: 0.4772. Min Act: -0.0000

Data Index: 1654040 (The Pile)

Max Activating Token Index: 279

Text #17

Max Range: 0.7502. Min Range: -0.7502

Max Act: 0.5205. Min Act: -0.0000

Data Index: 15681 (The Pile)

Max Activating Token Index: 730

Text #18

Max Range: 0.7502. Min Range: -0.7502

Max Act: 0.5045. Min Act: -0.0000

Data Index: 621650 (The Pile)

Max Activating Token Index: 420

Text #19

Max Range: 0.7502. Min Range: -0.7502

Max Act: 0.5041. Min Act: -0.0000

Data Index: 1924003 (The Pile)

Max Activating Token Index: 1016