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

Dataset: The Pile

Neuron 2667 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: 1.3722. Min Range: -1.3722

Max Act: 1.3722. Min Act: -0.0000

Data Index: 1772662 (The Pile)

Max Activating Token Index: 200

Text #1

Max Range: 1.3722. Min Range: -1.3722

Max Act: 1.1035. Min Act: -0.0000

Data Index: 865945 (The Pile)

Max Activating Token Index: 915

Text #2

Max Range: 1.3722. Min Range: -1.3722

Max Act: 1.0883. Min Act: -0.0000

Data Index: 656111 (The Pile)

Max Activating Token Index: 978

Text #3

Max Range: 1.3722. Min Range: -1.3722

Max Act: 1.0756. Min Act: -0.0000

Data Index: 1847461 (The Pile)

Max Activating Token Index: 63

Text #4

Max Range: 1.3722. Min Range: -1.3722

Max Act: 1.1037. Min Act: -0.0000

Data Index: 1102884 (The Pile)

Max Activating Token Index: 186

Text #5

Max Range: 1.3722. Min Range: -1.3722

Max Act: 1.0699. Min Act: -0.0000

Data Index: 1476422 (The Pile)

Max Activating Token Index: 588

Text #6

Max Range: 1.3722. Min Range: -1.3722

Max Act: 1.0653. Min Act: -0.0000

Data Index: 313691 (The Pile)

Max Activating Token Index: 315

Text #7

Max Range: 1.3722. Min Range: -1.3722

Max Act: 1.0223. Min Act: -0.0000

Data Index: 1118932 (The Pile)

Max Activating Token Index: 265

Text #8

Max Range: 1.3722. Min Range: -1.3722

Max Act: 1.1072. Min Act: -0.0000

Data Index: 1638447 (The Pile)

Max Activating Token Index: 899

Text #9

Max Range: 1.3722. Min Range: -1.3722

Max Act: 1.0332. Min Act: -0.0000

Data Index: 1595217 (The Pile)

Max Activating Token Index: 180

Text #10

Max Range: 1.3722. Min Range: -1.3722

Max Act: 1.0149. Min Act: -0.0000

Data Index: 1686556 (The Pile)

Max Activating Token Index: 242

Text #11

Max Range: 1.3722. Min Range: -1.3722

Max Act: 1.0016. Min Act: -0.0000

Data Index: 237919 (The Pile)

Max Activating Token Index: 116

Text #12

Max Range: 1.3722. Min Range: -1.3722

Max Act: 0.9986. Min Act: -0.0000

Data Index: 447906 (The Pile)

Max Activating Token Index: 570

Text #13

Max Range: 1.3722. Min Range: -1.3722

Max Act: 1.0601. Min Act: -0.0000

Data Index: 180586 (The Pile)

Max Activating Token Index: 828

Text #14

Max Range: 1.3722. Min Range: -1.3722

Max Act: 1.0369. Min Act: -0.0000

Data Index: 1668670 (The Pile)

Max Activating Token Index: 223

Text #15

Max Range: 1.3722. Min Range: -1.3722

Max Act: 0.9712. Min Act: -0.0000

Data Index: 1039146 (The Pile)

Max Activating Token Index: 827

Text #16

Max Range: 1.3722. Min Range: -1.3722

Max Act: 0.9651. Min Act: -0.0000

Data Index: 711293 (The Pile)

Max Activating Token Index: 530

Text #17

Max Range: 1.3722. Min Range: -1.3722

Max Act: 0.9290. Min Act: -0.0000

Data Index: 1499567 (The Pile)

Max Activating Token Index: 154

Text #18

Max Range: 1.3722. Min Range: -1.3722

Max Act: 0.9807. Min Act: -0.0000

Data Index: 1588908 (The Pile)

Max Activating Token Index: 390

Text #19

Max Range: 1.3722. Min Range: -1.3722

Max Act: 0.9520. Min Act: -0.0000

Data Index: 1321189 (The Pile)

Max Activating Token Index: 914