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

Dataset: The Pile

Neuron 3689 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: 0.8031. Min Range: -0.8031

Max Act: 0.8031. Min Act: -0.0000

Data Index: 319745 (The Pile)

Max Activating Token Index: 806

Text #1

Max Range: 0.8031. Min Range: -0.8031

Max Act: 0.7323. Min Act: -0.0000

Data Index: 178040 (The Pile)

Max Activating Token Index: 598

Text #2

Max Range: 0.8031. Min Range: -0.8031

Max Act: 0.6418. Min Act: -0.0000

Data Index: 482107 (The Pile)

Max Activating Token Index: 627

Text #3

Max Range: 0.8031. Min Range: -0.8031

Max Act: 0.6693. Min Act: -0.0000

Data Index: 1042599 (The Pile)

Max Activating Token Index: 918

Text #4

Max Range: 0.8031. Min Range: -0.8031

Max Act: 0.6832. Min Act: -0.0000

Data Index: 478450 (The Pile)

Max Activating Token Index: 143

Text #5

Max Range: 0.8031. Min Range: -0.8031

Max Act: 0.6873. Min Act: -0.0000

Data Index: 434796 (The Pile)

Max Activating Token Index: 840

Text #6

Max Range: 0.8031. Min Range: -0.8031

Max Act: 0.6014. Min Act: -0.0000

Data Index: 186865 (The Pile)

Max Activating Token Index: 427

Text #7

Max Range: 0.8031. Min Range: -0.8031

Max Act: 0.6278. Min Act: -0.0000

Data Index: 150673 (The Pile)

Max Activating Token Index: 450

Text #8

Max Range: 0.8031. Min Range: -0.8031

Max Act: 0.5901. Min Act: -0.0000

Data Index: 1133838 (The Pile)

Max Activating Token Index: 892

Text #9

Max Range: 0.8031. Min Range: -0.8031

Max Act: 0.5641. Min Act: -0.0000

Data Index: 237849 (The Pile)

Max Activating Token Index: 706

Text #10

Max Range: 0.8031. Min Range: -0.8031

Max Act: 0.5294. Min Act: -0.0000

Data Index: 76340 (The Pile)

Max Activating Token Index: 177

Text #11

Max Range: 0.8031. Min Range: -0.8031

Max Act: 0.5541. Min Act: -0.0000

Data Index: 17447 (The Pile)

Max Activating Token Index: 870

Text #12

Max Range: 0.8031. Min Range: -0.8031

Max Act: 0.5323. Min Act: -0.0000

Data Index: 10864 (The Pile)

Max Activating Token Index: 684

Text #13

Max Range: 0.8031. Min Range: -0.8031

Max Act: 0.5202. Min Act: -0.0000

Data Index: 494389 (The Pile)

Max Activating Token Index: 539

Text #14

Max Range: 0.8031. Min Range: -0.8031

Max Act: 0.5148. Min Act: -0.0000

Data Index: 1128773 (The Pile)

Max Activating Token Index: 378

Text #15

Max Range: 0.8031. Min Range: -0.8031

Max Act: 0.4838. Min Act: -0.0000

Data Index: 161842 (The Pile)

Max Activating Token Index: 163

Text #16

Max Range: 0.8031. Min Range: -0.8031

Max Act: 0.4980. Min Act: -0.0000

Data Index: 438932 (The Pile)

Max Activating Token Index: 396

Text #17

Max Range: 0.8031. Min Range: -0.8031

Max Act: 0.4727. Min Act: -0.0000

Data Index: 1977798 (The Pile)

Max Activating Token Index: 950

Text #18

Max Range: 0.8031. Min Range: -0.8031

Max Act: 0.4650. Min Act: -0.0000

Data Index: 318765 (The Pile)

Max Activating Token Index: 605

Text #19

Max Range: 0.8031. Min Range: -0.8031

Max Act: 0.4648. Min Act: -0.0000

Data Index: 1243227 (The Pile)

Max Activating Token Index: 937