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

Dataset: The Pile

Neuron 1996 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: 0.0782. Min Range: -0.0782

Max Act: 0.0782. Min Act: 0.0000

Data Index: 1266100 (The Pile)

Max Activating Token Index: 1023

Text #1

Max Range: 0.0782. Min Range: -0.0782

Max Act: 0.0767. Min Act: -0.0000

Data Index: 1252548 (The Pile)

Max Activating Token Index: 1023

Text #2

Max Range: 0.0782. Min Range: -0.0782

Max Act: 0.0736. Min Act: -0.0000

Data Index: 1171621 (The Pile)

Max Activating Token Index: 599

Text #3

Max Range: 0.0782. Min Range: -0.0782

Max Act: 0.0737. Min Act: -0.0000

Data Index: 733836 (The Pile)

Max Activating Token Index: 176

Text #4

Max Range: 0.0782. Min Range: -0.0782

Max Act: 0.0721. Min Act: -0.0000

Data Index: 1884665 (The Pile)

Max Activating Token Index: 308

Text #5

Max Range: 0.0782. Min Range: -0.0782

Max Act: 0.0710. Min Act: -0.0000

Data Index: 710811 (The Pile)

Max Activating Token Index: 255

Text #6

Max Range: 0.0782. Min Range: -0.0782

Max Act: 0.0708. Min Act: -0.0000

Data Index: 844350 (The Pile)

Max Activating Token Index: 1023

Text #7

Max Range: 0.0782. Min Range: -0.0782

Max Act: 0.0701. Min Act: -0.0000

Data Index: 1338073 (The Pile)

Max Activating Token Index: 1023

Text #8

Max Range: 0.0782. Min Range: -0.0782

Max Act: 0.0694. Min Act: -0.0000

Data Index: 982123 (The Pile)

Max Activating Token Index: 1023

Text #9

Max Range: 0.0782. Min Range: -0.0782

Max Act: 0.0692. Min Act: -0.0000

Data Index: 124351 (The Pile)

Max Activating Token Index: 770

Text #10

Max Range: 0.0782. Min Range: -0.0782

Max Act: 0.0689. Min Act: -0.0000

Data Index: 169846 (The Pile)

Max Activating Token Index: 1023

Text #11

Max Range: 0.0782. Min Range: -0.0782

Max Act: 0.0674. Min Act: -0.0000

Data Index: 618796 (The Pile)

Max Activating Token Index: 1023

Text #12

Max Range: 0.0782. Min Range: -0.0782

Max Act: 0.0669. Min Act: -0.0000

Data Index: 1305713 (The Pile)

Max Activating Token Index: 966

Text #13

Max Range: 0.0782. Min Range: -0.0782

Max Act: 0.0665. Min Act: -0.0000

Data Index: 1982341 (The Pile)

Max Activating Token Index: 1023

Text #14

Max Range: 0.0782. Min Range: -0.0782

Max Act: 0.0665. Min Act: 0.0000

Data Index: 924577 (The Pile)

Max Activating Token Index: 190

Text #15

Max Range: 0.0782. Min Range: -0.0782

Max Act: 0.0661. Min Act: 0.0000

Data Index: 1146582 (The Pile)

Max Activating Token Index: 463

Text #16

Max Range: 0.0782. Min Range: -0.0782

Max Act: 0.0658. Min Act: 0.0000

Data Index: 1254495 (The Pile)

Max Activating Token Index: 999

Text #17

Max Range: 0.0782. Min Range: -0.0782

Max Act: 0.0654. Min Act: -0.0000

Data Index: 808148 (The Pile)

Max Activating Token Index: 992

Text #18

Max Range: 0.0782. Min Range: -0.0782

Max Act: 0.0650. Min Act: -0.0000

Data Index: 1590750 (The Pile)

Max Activating Token Index: 1023

Text #19

Max Range: 0.0782. Min Range: -0.0782

Max Act: 0.0644. Min Act: -0.0000

Data Index: 950558 (The Pile)

Max Activating Token Index: 199