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

Dataset: The Pile

Neuron 3827 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: 0.1146. Min Range: -0.1146

Max Act: 0.1146. Min Act: -0.0000

Data Index: 1603476 (The Pile)

Max Activating Token Index: 9

Text #1

Max Range: 0.1146. Min Range: -0.1146

Max Act: 0.1100. Min Act: -0.0000

Data Index: 287997 (The Pile)

Max Activating Token Index: 5

Text #2

Max Range: 0.1146. Min Range: -0.1146

Max Act: 0.1031. Min Act: -0.0000

Data Index: 1720132 (The Pile)

Max Activating Token Index: 40

Text #3

Max Range: 0.1146. Min Range: -0.1146

Max Act: 0.0976. Min Act: -0.0000

Data Index: 773442 (The Pile)

Max Activating Token Index: 1023

Text #4

Max Range: 0.1146. Min Range: -0.1146

Max Act: 0.0993. Min Act: -0.0000

Data Index: 835650 (The Pile)

Max Activating Token Index: 3

Text #5

Max Range: 0.1146. Min Range: -0.1146

Max Act: 0.0953. Min Act: -0.0000

Data Index: 1738553 (The Pile)

Max Activating Token Index: 1023

Text #6

Max Range: 0.1146. Min Range: -0.1146

Max Act: 0.0950. Min Act: -0.0000

Data Index: 1174380 (The Pile)

Max Activating Token Index: 58

Text #7

Max Range: 0.1146. Min Range: -0.1146

Max Act: 0.0913. Min Act: -0.0000

Data Index: 473592 (The Pile)

Max Activating Token Index: 8

Text #8

Max Range: 0.1146. Min Range: -0.1146

Max Act: 0.0892. Min Act: -0.0000

Data Index: 158478 (The Pile)

Max Activating Token Index: 23

Text #9

Max Range: 0.1146. Min Range: -0.1146

Max Act: 0.0890. Min Act: 0.0000

Data Index: 1699146 (The Pile)

Max Activating Token Index: 640

Text #10

Max Range: 0.1146. Min Range: -0.1146

Max Act: 0.0880. Min Act: 0.0000

Data Index: 280276 (The Pile)

Max Activating Token Index: 15

Text #11

Max Range: 0.1146. Min Range: -0.1146

Max Act: 0.0875. Min Act: 0.0000

Data Index: 719854 (The Pile)

Max Activating Token Index: 1023

Text #12

Max Range: 0.1146. Min Range: -0.1146

Max Act: 0.0874. Min Act: -0.0000

Data Index: 894394 (The Pile)

Max Activating Token Index: 48

Text #13

Max Range: 0.1146. Min Range: -0.1146

Max Act: 0.0870. Min Act: 0.0000

Data Index: 199876 (The Pile)

Max Activating Token Index: 1023

Text #14

Max Range: 0.1146. Min Range: -0.1146

Max Act: 0.0867. Min Act: -0.0000

Data Index: 601315 (The Pile)

Max Activating Token Index: 70

Text #15

Max Range: 0.1146. Min Range: -0.1146

Max Act: 0.0865. Min Act: -0.0000

Data Index: 307810 (The Pile)

Max Activating Token Index: 1023

Text #16

Max Range: 0.1146. Min Range: -0.1146

Max Act: 0.0862. Min Act: -0.0000

Data Index: 1895877 (The Pile)

Max Activating Token Index: 32

Text #17

Max Range: 0.1146. Min Range: -0.1146

Max Act: 0.0859. Min Act: -0.0000

Data Index: 1649157 (The Pile)

Max Activating Token Index: 32

Text #18

Max Range: 0.1146. Min Range: -0.1146

Max Act: 0.0885. Min Act: -0.0000

Data Index: 1067578 (The Pile)

Max Activating Token Index: 4

Text #19

Max Range: 0.1146. Min Range: -0.1146

Max Act: 0.0872. Min Act: -0.0000

Data Index: 191761 (The Pile)

Max Activating Token Index: 204