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

Dataset: The Pile

Neuron 4627 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7047. Min Range: -1.7047

Max Act: 1.7047. Min Act: -0.0000

Data Index: 1315984 (The Pile)

Max Activating Token Index: 1007

Text #1

Max Range: 1.7047. Min Range: -1.7047

Max Act: 1.3391. Min Act: -0.0000

Data Index: 104339 (The Pile)

Max Activating Token Index: 683

Text #2

Max Range: 1.7047. Min Range: -1.7047

Max Act: 1.1570. Min Act: -0.0000

Data Index: 547844 (The Pile)

Max Activating Token Index: 138

Text #3

Max Range: 1.7047. Min Range: -1.7047

Max Act: 1.2397. Min Act: -0.0000

Data Index: 1154289 (The Pile)

Max Activating Token Index: 390

Text #4

Max Range: 1.7047. Min Range: -1.7047

Max Act: 1.2457. Min Act: -0.0000

Data Index: 1944420 (The Pile)

Max Activating Token Index: 1012

Text #5

Max Range: 1.7047. Min Range: -1.7047

Max Act: 1.1851. Min Act: -0.0000

Data Index: 35318 (The Pile)

Max Activating Token Index: 27

Text #6

Max Range: 1.7047. Min Range: -1.7047

Max Act: 1.0604. Min Act: -0.0000

Data Index: 1071716 (The Pile)

Max Activating Token Index: 550

Text #7

Max Range: 1.7047. Min Range: -1.7047

Max Act: 1.1158. Min Act: -0.0000

Data Index: 1636653 (The Pile)

Max Activating Token Index: 100

Text #8

Max Range: 1.7047. Min Range: -1.7047

Max Act: 1.1552. Min Act: -0.0000

Data Index: 636608 (The Pile)

Max Activating Token Index: 359

Text #9

Max Range: 1.7047. Min Range: -1.7047

Max Act: 1.0710. Min Act: -0.0000

Data Index: 1616653 (The Pile)

Max Activating Token Index: 776

Text #10

Max Range: 1.7047. Min Range: -1.7047

Max Act: 1.0694. Min Act: -0.0000

Data Index: 595800 (The Pile)

Max Activating Token Index: 464

Text #11

Max Range: 1.7047. Min Range: -1.7047

Max Act: 0.8997. Min Act: -0.0000

Data Index: 475792 (The Pile)

Max Activating Token Index: 936

Text #12

Max Range: 1.7047. Min Range: -1.7047

Max Act: 0.9909. Min Act: -0.0000

Data Index: 1455262 (The Pile)

Max Activating Token Index: 765

Text #13

Max Range: 1.7047. Min Range: -1.7047

Max Act: 0.9072. Min Act: -0.0000

Data Index: 939181 (The Pile)

Max Activating Token Index: 124

Text #14

Max Range: 1.7047. Min Range: -1.7047

Max Act: 0.9270. Min Act: -0.0000

Data Index: 499881 (The Pile)

Max Activating Token Index: 970

Text #15

Max Range: 1.7047. Min Range: -1.7047

Max Act: 1.0305. Min Act: -0.0000

Data Index: 1207038 (The Pile)

Max Activating Token Index: 847

Text #16

Max Range: 1.7047. Min Range: -1.7047

Max Act: 0.9981. Min Act: -0.0000

Data Index: 389250 (The Pile)

Max Activating Token Index: 741

Text #17

Max Range: 1.7047. Min Range: -1.7047

Max Act: 1.0628. Min Act: -0.0000

Data Index: 1888057 (The Pile)

Max Activating Token Index: 242

Text #18

Max Range: 1.7047. Min Range: -1.7047

Max Act: 0.9834. Min Act: -0.0000

Data Index: 380288 (The Pile)

Max Activating Token Index: 173

Text #19

Max Range: 1.7047. Min Range: -1.7047

Max Act: 0.9629. Min Act: -0.0000

Data Index: 1603713 (The Pile)

Max Activating Token Index: 783