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

Dataset: The Pile

Neuron 4081 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: 0.0945. Min Range: -0.0945

Max Act: 0.0945. Min Act: -0.0000

Data Index: 884780 (The Pile)

Max Activating Token Index: 4

Text #1

Max Range: 0.0945. Min Range: -0.0945

Max Act: 0.0904. Min Act: 0.0000

Data Index: 876654 (The Pile)

Max Activating Token Index: 1023

Text #2

Max Range: 0.0945. Min Range: -0.0945

Max Act: 0.0871. Min Act: -0.0000

Data Index: 1134181 (The Pile)

Max Activating Token Index: 1023

Text #3

Max Range: 0.0945. Min Range: -0.0945

Max Act: 0.0828. Min Act: 0.0000

Data Index: 1347993 (The Pile)

Max Activating Token Index: 1023

Text #4

Max Range: 0.0945. Min Range: -0.0945

Max Act: 0.0822. Min Act: -0.0000

Data Index: 912224 (The Pile)

Max Activating Token Index: 6

Text #5

Max Range: 0.0945. Min Range: -0.0945

Max Act: 0.0851. Min Act: 0.0000

Data Index: 1523842 (The Pile)

Max Activating Token Index: 1023

Text #6

Max Range: 0.0945. Min Range: -0.0945

Max Act: 0.0819. Min Act: 0.0000

Data Index: 752250 (The Pile)

Max Activating Token Index: 1023

Text #7

Max Range: 0.0945. Min Range: -0.0945

Max Act: 0.0804. Min Act: 0.0000

Data Index: 1722927 (The Pile)

Max Activating Token Index: 1023

Text #8

Max Range: 0.0945. Min Range: -0.0945

Max Act: 0.0795. Min Act: 0.0000

Data Index: 908999 (The Pile)

Max Activating Token Index: 1023

Text #9

Max Range: 0.0945. Min Range: -0.0945

Max Act: 0.0782. Min Act: -0.0000

Data Index: 19792 (The Pile)

Max Activating Token Index: 1023

Text #10

Max Range: 0.0945. Min Range: -0.0945

Max Act: 0.0777. Min Act: 0.0000

Data Index: 1133488 (The Pile)

Max Activating Token Index: 1023

Text #11

Max Range: 0.0945. Min Range: -0.0945

Max Act: 0.0775. Min Act: 0.0000

Data Index: 1833348 (The Pile)

Max Activating Token Index: 1023

Text #12

Max Range: 0.0945. Min Range: -0.0945

Max Act: 0.0774. Min Act: -0.0000

Data Index: 171411 (The Pile)

Max Activating Token Index: 1023

Text #13

Max Range: 0.0945. Min Range: -0.0945

Max Act: 0.0769. Min Act: 0.0000

Data Index: 331703 (The Pile)

Max Activating Token Index: 665

Text #14

Max Range: 0.0945. Min Range: -0.0945

Max Act: 0.0770. Min Act: -0.0000

Data Index: 1319271 (The Pile)

Max Activating Token Index: 1023

Text #15

Max Range: 0.0945. Min Range: -0.0945

Max Act: 0.0766. Min Act: -0.0000

Data Index: 1127 (The Pile)

Max Activating Token Index: 13

Text #16

Max Range: 0.0945. Min Range: -0.0945

Max Act: 0.0766. Min Act: 0.0000

Data Index: 108460 (The Pile)

Max Activating Token Index: 6

Text #17

Max Range: 0.0945. Min Range: -0.0945

Max Act: 0.0764. Min Act: -0.0000

Data Index: 426193 (The Pile)

Max Activating Token Index: 1023

Text #18

Max Range: 0.0945. Min Range: -0.0945

Max Act: 0.0762. Min Act: 0.0000

Data Index: 99350 (The Pile)

Max Activating Token Index: 8

Text #19

Max Range: 0.0945. Min Range: -0.0945

Max Act: 0.0760. Min Act: 0.0000

Data Index: 476956 (The Pile)

Max Activating Token Index: 1023