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

Dataset: The Pile

Neuron 3367 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: 3.9600. Min Range: -3.9600

Max Act: 3.9600. Min Act: -0.0000

Data Index: 1910181 (The Pile)

Max Activating Token Index: 733

Text #1

Max Range: 3.9600. Min Range: -3.9600

Max Act: 3.6403. Min Act: -0.0000

Data Index: 269132 (The Pile)

Max Activating Token Index: 623

Text #2

Max Range: 3.9600. Min Range: -3.9600

Max Act: 3.6735. Min Act: -0.0000

Data Index: 1457138 (The Pile)

Max Activating Token Index: 616

Text #3

Max Range: 3.9600. Min Range: -3.9600

Max Act: 3.4115. Min Act: -0.0000

Data Index: 535934 (The Pile)

Max Activating Token Index: 570

Text #4

Max Range: 3.9600. Min Range: -3.9600

Max Act: 3.5220. Min Act: -0.0000

Data Index: 284715 (The Pile)

Max Activating Token Index: 90

Text #5

Max Range: 3.9600. Min Range: -3.9600

Max Act: 3.4978. Min Act: -0.0000

Data Index: 1262052 (The Pile)

Max Activating Token Index: 259

Text #6

Max Range: 3.9600. Min Range: -3.9600

Max Act: 3.5588. Min Act: -0.0000

Data Index: 1713633 (The Pile)

Max Activating Token Index: 627

Text #7

Max Range: 3.9600. Min Range: -3.9600

Max Act: 3.2702. Min Act: -0.0000

Data Index: 952117 (The Pile)

Max Activating Token Index: 846

Text #8

Max Range: 3.9600. Min Range: -3.9600

Max Act: 3.3852. Min Act: 0.0000

Data Index: 1506308 (The Pile)

Max Activating Token Index: 415

Text #9

Max Range: 3.9600. Min Range: -3.9600

Max Act: 3.3822. Min Act: -0.0000

Data Index: 1874210 (The Pile)

Max Activating Token Index: 1009

Text #10

Max Range: 3.9600. Min Range: -3.9600

Max Act: 3.1893. Min Act: -0.0000

Data Index: 402604 (The Pile)

Max Activating Token Index: 570

Text #11

Max Range: 3.9600. Min Range: -3.9600

Max Act: 3.1831. Min Act: -0.0000

Data Index: 435039 (The Pile)

Max Activating Token Index: 86

Text #12

Max Range: 3.9600. Min Range: -3.9600

Max Act: 3.3695. Min Act: -0.0000

Data Index: 515496 (The Pile)

Max Activating Token Index: 911

Text #13

Max Range: 3.9600. Min Range: -3.9600

Max Act: 3.2887. Min Act: -0.0000

Data Index: 800624 (The Pile)

Max Activating Token Index: 354

Text #14

Max Range: 3.9600. Min Range: -3.9600

Max Act: 3.2942. Min Act: -0.0000

Data Index: 1941060 (The Pile)

Max Activating Token Index: 885

Text #15

Max Range: 3.9600. Min Range: -3.9600

Max Act: 3.4262. Min Act: -0.0000

Data Index: 582599 (The Pile)

Max Activating Token Index: 415

Text #16

Max Range: 3.9600. Min Range: -3.9600

Max Act: 3.2708. Min Act: 0.0000

Data Index: 588321 (The Pile)

Max Activating Token Index: 593

Text #17

Max Range: 3.9600. Min Range: -3.9600

Max Act: 3.1006. Min Act: -0.0000

Data Index: 1680055 (The Pile)

Max Activating Token Index: 486

Text #18

Max Range: 3.9600. Min Range: -3.9600

Max Act: 3.2113. Min Act: -0.0000

Data Index: 1412791 (The Pile)

Max Activating Token Index: 568

Text #19

Max Range: 3.9600. Min Range: -3.9600

Max Act: 3.2088. Min Act: 0.0000

Data Index: 232604 (The Pile)

Max Activating Token Index: 582