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

Dataset: The Pile

Neuron 3079 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: 0.8732. Min Range: -0.8732

Max Act: 0.8732. Min Act: -0.0000

Data Index: 488095 (The Pile)

Max Activating Token Index: 992

Text #1

Max Range: 0.8732. Min Range: -0.8732

Max Act: 0.7708. Min Act: -0.0000

Data Index: 1594133 (The Pile)

Max Activating Token Index: 710

Text #2

Max Range: 0.8732. Min Range: -0.8732

Max Act: 0.7427. Min Act: -0.0000

Data Index: 498475 (The Pile)

Max Activating Token Index: 149

Text #3

Max Range: 0.8732. Min Range: -0.8732

Max Act: 0.7209. Min Act: -0.0000

Data Index: 1747989 (The Pile)

Max Activating Token Index: 49

Text #4

Max Range: 0.8732. Min Range: -0.8732

Max Act: 0.6928. Min Act: -0.0000

Data Index: 761841 (The Pile)

Max Activating Token Index: 311

Text #5

Max Range: 0.8732. Min Range: -0.8732

Max Act: 0.6762. Min Act: 0.0000

Data Index: 968328 (The Pile)

Max Activating Token Index: 915

Text #6

Max Range: 0.8732. Min Range: -0.8732

Max Act: 0.6567. Min Act: -0.0000

Data Index: 777388 (The Pile)

Max Activating Token Index: 1016

Text #7

Max Range: 0.8732. Min Range: -0.8732

Max Act: 0.6886. Min Act: 0.0000

Data Index: 146903 (The Pile)

Max Activating Token Index: 264

Text #8

Max Range: 0.8732. Min Range: -0.8732

Max Act: 0.6682. Min Act: -0.0000

Data Index: 945052 (The Pile)

Max Activating Token Index: 350

Text #9

Max Range: 0.8732. Min Range: -0.8732

Max Act: 0.6616. Min Act: -0.0000

Data Index: 1347036 (The Pile)

Max Activating Token Index: 149

Text #10

Max Range: 0.8732. Min Range: -0.8732

Max Act: 0.6580. Min Act: -0.0000

Data Index: 928455 (The Pile)

Max Activating Token Index: 1008

Text #11

Max Range: 0.8732. Min Range: -0.8732

Max Act: 0.6262. Min Act: -0.0000

Data Index: 878157 (The Pile)

Max Activating Token Index: 564

Text #12

Max Range: 0.8732. Min Range: -0.8732

Max Act: 0.5990. Min Act: 0.0000

Data Index: 1579228 (The Pile)

Max Activating Token Index: 767

Text #13

Max Range: 0.8732. Min Range: -0.8732

Max Act: 0.6112. Min Act: -0.0000

Data Index: 1154863 (The Pile)

Max Activating Token Index: 100

Text #14

Max Range: 0.8732. Min Range: -0.8732

Max Act: 0.6306. Min Act: -0.0000

Data Index: 1927333 (The Pile)

Max Activating Token Index: 791

Text #15

Max Range: 0.8732. Min Range: -0.8732

Max Act: 0.6004. Min Act: -0.0000

Data Index: 1235206 (The Pile)

Max Activating Token Index: 92

Text #16

Max Range: 0.8732. Min Range: -0.8732

Max Act: 0.5862. Min Act: -0.0000

Data Index: 1544315 (The Pile)

Max Activating Token Index: 507

Text #17

Max Range: 0.8732. Min Range: -0.8732

Max Act: 0.6029. Min Act: -0.0000

Data Index: 641300 (The Pile)

Max Activating Token Index: 89

Text #18

Max Range: 0.8732. Min Range: -0.8732

Max Act: 0.5949. Min Act: -0.0000

Data Index: 1821900 (The Pile)

Max Activating Token Index: 741

Text #19

Max Range: 0.8732. Min Range: -0.8732

Max Act: 0.5289. Min Act: 0.0000

Data Index: 1900253 (The Pile)

Max Activating Token Index: 676