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

Dataset: The Pile

Neuron 3233 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8745. Min Range: -0.8745

Max Act: 0.8745. Min Act: -0.0000

Data Index: 232372 (The Pile)

Max Activating Token Index: 472

Text #1

Max Range: 0.8745. Min Range: -0.8745

Max Act: 0.7629. Min Act: -0.0000

Data Index: 1278154 (The Pile)

Max Activating Token Index: 27

Text #2

Max Range: 0.8745. Min Range: -0.8745

Max Act: 0.7909. Min Act: 0.0000

Data Index: 634287 (The Pile)

Max Activating Token Index: 299

Text #3

Max Range: 0.8745. Min Range: -0.8745

Max Act: 0.6839. Min Act: -0.0000

Data Index: 718778 (The Pile)

Max Activating Token Index: 146

Text #4

Max Range: 0.8745. Min Range: -0.8745

Max Act: 0.5190. Min Act: -0.0000

Data Index: 1533905 (The Pile)

Max Activating Token Index: 535

Text #5

Max Range: 0.8745. Min Range: -0.8745

Max Act: 0.6031. Min Act: -0.0000

Data Index: 1892523 (The Pile)

Max Activating Token Index: 462

Text #6

Max Range: 0.8745. Min Range: -0.8745

Max Act: 0.6237. Min Act: -0.0000

Data Index: 609241 (The Pile)

Max Activating Token Index: 173

Text #7

Max Range: 0.8745. Min Range: -0.8745

Max Act: 0.5653. Min Act: -0.0000

Data Index: 975787 (The Pile)

Max Activating Token Index: 159

Text #8

Max Range: 0.8745. Min Range: -0.8745

Max Act: 0.6501. Min Act: -0.0000

Data Index: 1673015 (The Pile)

Max Activating Token Index: 649

Text #9

Max Range: 0.8745. Min Range: -0.8745

Max Act: 0.5880. Min Act: -0.0000

Data Index: 820191 (The Pile)

Max Activating Token Index: 690

Text #10

Max Range: 0.8745. Min Range: -0.8745

Max Act: 0.5528. Min Act: -0.0000

Data Index: 983325 (The Pile)

Max Activating Token Index: 462

Text #11

Max Range: 0.8745. Min Range: -0.8745

Max Act: 0.5192. Min Act: -0.0000

Data Index: 1415561 (The Pile)

Max Activating Token Index: 155

Text #12

Max Range: 0.8745. Min Range: -0.8745

Max Act: 0.5798. Min Act: 0.0000

Data Index: 1638227 (The Pile)

Max Activating Token Index: 323

Text #13

Max Range: 0.8745. Min Range: -0.8745

Max Act: 0.5131. Min Act: 0.0000

Data Index: 555331 (The Pile)

Max Activating Token Index: 387

Text #14

Max Range: 0.8745. Min Range: -0.8745

Max Act: 0.4877. Min Act: -0.0000

Data Index: 275679 (The Pile)

Max Activating Token Index: 825

Text #15

Max Range: 0.8745. Min Range: -0.8745

Max Act: 0.5108. Min Act: -0.0000

Data Index: 1684583 (The Pile)

Max Activating Token Index: 531

Text #16

Max Range: 0.8745. Min Range: -0.8745

Max Act: 0.5388. Min Act: -0.0000

Data Index: 1357441 (The Pile)

Max Activating Token Index: 304

Text #17

Max Range: 0.8745. Min Range: -0.8745

Max Act: 0.5094. Min Act: -0.0000

Data Index: 1069577 (The Pile)

Max Activating Token Index: 232

Text #18

Max Range: 0.8745. Min Range: -0.8745

Max Act: 0.5021. Min Act: -0.0000

Data Index: 1687152 (The Pile)

Max Activating Token Index: 314

Text #19

Max Range: 0.8745. Min Range: -0.8745

Max Act: 0.5294. Min Act: -0.0000

Data Index: 1725617 (The Pile)

Max Activating Token Index: 542