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

Dataset: The Pile

Neuron 5086 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: 0.0997. Min Range: -0.0997

Max Act: 0.0997. Min Act: 0.0000

Data Index: 1298278 (The Pile)

Max Activating Token Index: 1023

Text #1

Max Range: 0.0997. Min Range: -0.0997

Max Act: 0.0969. Min Act: -0.0000

Data Index: 43265 (The Pile)

Max Activating Token Index: 1023

Text #2

Max Range: 0.0997. Min Range: -0.0997

Max Act: 0.0933. Min Act: 0.0000

Data Index: 675854 (The Pile)

Max Activating Token Index: 1023

Text #3

Max Range: 0.0997. Min Range: -0.0997

Max Act: 0.0924. Min Act: 0.0000

Data Index: 535557 (The Pile)

Max Activating Token Index: 1023

Text #4

Max Range: 0.0997. Min Range: -0.0997

Max Act: 0.0904. Min Act: -0.0000

Data Index: 1775713 (The Pile)

Max Activating Token Index: 1023

Text #5

Max Range: 0.0997. Min Range: -0.0997

Max Act: 0.0902. Min Act: 0.0000

Data Index: 1014156 (The Pile)

Max Activating Token Index: 1023

Text #6

Max Range: 0.0997. Min Range: -0.0997

Max Act: 0.0900. Min Act: -0.0000

Data Index: 1293010 (The Pile)

Max Activating Token Index: 1023

Text #7

Max Range: 0.0997. Min Range: -0.0997

Max Act: 0.0927. Min Act: 0.0000

Data Index: 512288 (The Pile)

Max Activating Token Index: 1023

Text #8

Max Range: 0.0997. Min Range: -0.0997

Max Act: 0.0893. Min Act: 0.0000

Data Index: 1922523 (The Pile)

Max Activating Token Index: 1023

Text #9

Max Range: 0.0997. Min Range: -0.0997

Max Act: 0.0889. Min Act: -0.0000

Data Index: 1882082 (The Pile)

Max Activating Token Index: 1023

Text #10

Max Range: 0.0997. Min Range: -0.0997

Max Act: 0.0881. Min Act: 0.0000

Data Index: 1680328 (The Pile)

Max Activating Token Index: 1023

Text #11

Max Range: 0.0997. Min Range: -0.0997

Max Act: 0.0880. Min Act: 0.0000

Data Index: 499522 (The Pile)

Max Activating Token Index: 1023

Text #12

Max Range: 0.0997. Min Range: -0.0997

Max Act: 0.0848. Min Act: 0.0000

Data Index: 1180657 (The Pile)

Max Activating Token Index: 1023

Text #13

Max Range: 0.0997. Min Range: -0.0997

Max Act: 0.0878. Min Act: 0.0000

Data Index: 1442874 (The Pile)

Max Activating Token Index: 1023

Text #14

Max Range: 0.0997. Min Range: -0.0997

Max Act: 0.0872. Min Act: -0.0000

Data Index: 361176 (The Pile)

Max Activating Token Index: 1023

Text #15

Max Range: 0.0997. Min Range: -0.0997

Max Act: 0.0869. Min Act: -0.0000

Data Index: 1903469 (The Pile)

Max Activating Token Index: 1023

Text #16

Max Range: 0.0997. Min Range: -0.0997

Max Act: 0.0871. Min Act: 0.0000

Data Index: 912723 (The Pile)

Max Activating Token Index: 1023

Text #17

Max Range: 0.0997. Min Range: -0.0997

Max Act: 0.0863. Min Act: 0.0000

Data Index: 38742 (The Pile)

Max Activating Token Index: 1023

Text #18

Max Range: 0.0997. Min Range: -0.0997

Max Act: 0.0823. Min Act: -0.0000

Data Index: 745059 (The Pile)

Max Activating Token Index: 1023

Text #19

Max Range: 0.0997. Min Range: -0.0997

Max Act: 0.0840. Min Act: -0.0000

Data Index: 1856186 (The Pile)

Max Activating Token Index: 1023