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

Dataset: The Pile

Neuron 2646 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5638. Min Range: -0.5638

Max Act: 0.5411. Min Act: -0.0000

Data Index: 1385853 (The Pile)

Max Activating Token Index: 657

Text #1

Max Range: 0.5638. Min Range: -0.5638

Max Act: 0.5638. Min Act: -0.0000

Data Index: 1673686 (The Pile)

Max Activating Token Index: 578

Text #2

Max Range: 0.5638. Min Range: -0.5638

Max Act: 0.5568. Min Act: -0.0000

Data Index: 1388069 (The Pile)

Max Activating Token Index: 568

Text #3

Max Range: 0.5638. Min Range: -0.5638

Max Act: 0.5419. Min Act: -0.0000

Data Index: 321522 (The Pile)

Max Activating Token Index: 77

Text #4

Max Range: 0.5638. Min Range: -0.5638

Max Act: 0.5037. Min Act: -0.0000

Data Index: 484217 (The Pile)

Max Activating Token Index: 754

Text #5

Max Range: 0.5638. Min Range: -0.5638

Max Act: 0.5145. Min Act: -0.0000

Data Index: 147027 (The Pile)

Max Activating Token Index: 730

Text #6

Max Range: 0.5638. Min Range: -0.5638

Max Act: 0.5275. Min Act: -0.0000

Data Index: 487076 (The Pile)

Max Activating Token Index: 492

Text #7

Max Range: 0.5638. Min Range: -0.5638

Max Act: 0.5090. Min Act: -0.0000

Data Index: 301726 (The Pile)

Max Activating Token Index: 15

Text #8

Max Range: 0.5638. Min Range: -0.5638

Max Act: 0.4931. Min Act: -0.0000

Data Index: 707477 (The Pile)

Max Activating Token Index: 227

Text #9

Max Range: 0.5638. Min Range: -0.5638

Max Act: 0.5040. Min Act: -0.0000

Data Index: 1867010 (The Pile)

Max Activating Token Index: 294

Text #10

Max Range: 0.5638. Min Range: -0.5638

Max Act: 0.5101. Min Act: -0.0000

Data Index: 1318422 (The Pile)

Max Activating Token Index: 152

Text #11

Max Range: 0.5638. Min Range: -0.5638

Max Act: 0.5007. Min Act: -0.0000

Data Index: 490323 (The Pile)

Max Activating Token Index: 347

Text #12

Max Range: 0.5638. Min Range: -0.5638

Max Act: 0.5005. Min Act: -0.0000

Data Index: 991622 (The Pile)

Max Activating Token Index: 234

Text #13

Max Range: 0.5638. Min Range: -0.5638

Max Act: 0.4955. Min Act: -0.0000

Data Index: 1966246 (The Pile)

Max Activating Token Index: 90

Text #14

Max Range: 0.5638. Min Range: -0.5638

Max Act: 0.4981. Min Act: -0.0000

Data Index: 1239831 (The Pile)

Max Activating Token Index: 342

Text #15

Max Range: 0.5638. Min Range: -0.5638

Max Act: 0.4964. Min Act: -0.0000

Data Index: 1907613 (The Pile)

Max Activating Token Index: 38

Text #16

Max Range: 0.5638. Min Range: -0.5638

Max Act: 0.4781. Min Act: -0.0000

Data Index: 1969594 (The Pile)

Max Activating Token Index: 371

Text #17

Max Range: 0.5638. Min Range: -0.5638

Max Act: 0.4753. Min Act: -0.0000

Data Index: 1528513 (The Pile)

Max Activating Token Index: 110

Text #18

Max Range: 0.5638. Min Range: -0.5638

Max Act: 0.4784. Min Act: -0.0000

Data Index: 1613093 (The Pile)

Max Activating Token Index: 542

Text #19

Max Range: 0.5638. Min Range: -0.5638

Max Act: 0.4747. Min Act: -0.0000

Data Index: 1817997 (The Pile)

Max Activating Token Index: 857