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

Dataset: The Pile

Neuron 4133 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0746. Min Range: -0.0746

Max Act: 0.0746. Min Act: -0.0000

Data Index: 567553 (The Pile)

Max Activating Token Index: 1023

Text #1

Max Range: 0.0746. Min Range: -0.0746

Max Act: 0.0727. Min Act: -0.0000

Data Index: 1206933 (The Pile)

Max Activating Token Index: 1023

Text #2

Max Range: 0.0746. Min Range: -0.0746

Max Act: 0.0694. Min Act: 0.0000

Data Index: 1718149 (The Pile)

Max Activating Token Index: 1023

Text #3

Max Range: 0.0746. Min Range: -0.0746

Max Act: 0.0681. Min Act: -0.0000

Data Index: 1437723 (The Pile)

Max Activating Token Index: 1023

Text #4

Max Range: 0.0746. Min Range: -0.0746

Max Act: 0.0678. Min Act: -0.0000

Data Index: 1307315 (The Pile)

Max Activating Token Index: 1023

Text #5

Max Range: 0.0746. Min Range: -0.0746

Max Act: 0.0669. Min Act: -0.0000

Data Index: 1017809 (The Pile)

Max Activating Token Index: 1023

Text #6

Max Range: 0.0746. Min Range: -0.0746

Max Act: 0.0660. Min Act: -0.0000

Data Index: 1284042 (The Pile)

Max Activating Token Index: 1023

Text #7

Max Range: 0.0746. Min Range: -0.0746

Max Act: 0.0658. Min Act: -0.0000

Data Index: 1302802 (The Pile)

Max Activating Token Index: 1023

Text #8

Max Range: 0.0746. Min Range: -0.0746

Max Act: 0.0658. Min Act: -0.0000

Data Index: 564404 (The Pile)

Max Activating Token Index: 1023

Text #9

Max Range: 0.0746. Min Range: -0.0746

Max Act: 0.0680. Min Act: -0.0000

Data Index: 1667081 (The Pile)

Max Activating Token Index: 1023

Text #10

Max Range: 0.0746. Min Range: -0.0746

Max Act: 0.0654. Min Act: 0.0000

Data Index: 126272 (The Pile)

Max Activating Token Index: 1023

Text #11

Max Range: 0.0746. Min Range: -0.0746

Max Act: 0.0654. Min Act: 0.0000

Data Index: 53779 (The Pile)

Max Activating Token Index: 1023

Text #12

Max Range: 0.0746. Min Range: -0.0746

Max Act: 0.0649. Min Act: -0.0000

Data Index: 828475 (The Pile)

Max Activating Token Index: 1023

Text #13

Max Range: 0.0746. Min Range: -0.0746

Max Act: 0.0649. Min Act: -0.0000

Data Index: 242777 (The Pile)

Max Activating Token Index: 1023

Text #14

Max Range: 0.0746. Min Range: -0.0746

Max Act: 0.0643. Min Act: -0.0000

Data Index: 1015918 (The Pile)

Max Activating Token Index: 1023

Text #15

Max Range: 0.0746. Min Range: -0.0746

Max Act: 0.0640. Min Act: 0.0000

Data Index: 143584 (The Pile)

Max Activating Token Index: 1023

Text #16

Max Range: 0.0746. Min Range: -0.0746

Max Act: 0.0637. Min Act: -0.0000

Data Index: 1465876 (The Pile)

Max Activating Token Index: 1023

Text #17

Max Range: 0.0746. Min Range: -0.0746

Max Act: 0.0633. Min Act: 0.0000

Data Index: 340763 (The Pile)

Max Activating Token Index: 1023

Text #18

Max Range: 0.0746. Min Range: -0.0746

Max Act: 0.0632. Min Act: 0.0000

Data Index: 597829 (The Pile)

Max Activating Token Index: 1023

Text #19

Max Range: 0.0746. Min Range: -0.0746

Max Act: 0.0628. Min Act: -0.0000

Data Index: 1693046 (The Pile)

Max Activating Token Index: 1023