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

Dataset: The Pile

Neuron 4652 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: 0.1152. Min Range: -0.1152

Max Act: 0.1152. Min Act: -0.0000

Data Index: 994359 (The Pile)

Max Activating Token Index: 12

Text #1

Max Range: 0.1152. Min Range: -0.1152

Max Act: 0.1092. Min Act: -0.0000

Data Index: 602787 (The Pile)

Max Activating Token Index: 22

Text #2

Max Range: 0.1152. Min Range: -0.1152

Max Act: 0.1028. Min Act: -0.0000

Data Index: 1645625 (The Pile)

Max Activating Token Index: 8

Text #3

Max Range: 0.1152. Min Range: -0.1152

Max Act: 0.1023. Min Act: -0.0000

Data Index: 147411 (The Pile)

Max Activating Token Index: 17

Text #4

Max Range: 0.1152. Min Range: -0.1152

Max Act: 0.1013. Min Act: -0.0000

Data Index: 119506 (The Pile)

Max Activating Token Index: 21

Text #5

Max Range: 0.1152. Min Range: -0.1152

Max Act: 0.1010. Min Act: -0.0000

Data Index: 1050960 (The Pile)

Max Activating Token Index: 13

Text #6

Max Range: 0.1152. Min Range: -0.1152

Max Act: 0.1007. Min Act: -0.0000

Data Index: 67864 (The Pile)

Max Activating Token Index: 1023

Text #7

Max Range: 0.1152. Min Range: -0.1152

Max Act: 0.0990. Min Act: -0.0000

Data Index: 1648321 (The Pile)

Max Activating Token Index: 24

Text #8

Max Range: 0.1152. Min Range: -0.1152

Max Act: 0.0979. Min Act: -0.0000

Data Index: 1893308 (The Pile)

Max Activating Token Index: 42

Text #9

Max Range: 0.1152. Min Range: -0.1152

Max Act: 0.0957. Min Act: -0.0000

Data Index: 333700 (The Pile)

Max Activating Token Index: 18

Text #10

Max Range: 0.1152. Min Range: -0.1152

Max Act: 0.0955. Min Act: -0.0000

Data Index: 278215 (The Pile)

Max Activating Token Index: 12

Text #11

Max Range: 0.1152. Min Range: -0.1152

Max Act: 0.0954. Min Act: -0.0000

Data Index: 936875 (The Pile)

Max Activating Token Index: 1023

Text #12

Max Range: 0.1152. Min Range: -0.1152

Max Act: 0.0917. Min Act: -0.0000

Data Index: 1683270 (The Pile)

Max Activating Token Index: 1023

Text #13

Max Range: 0.1152. Min Range: -0.1152

Max Act: 0.0916. Min Act: -0.0000

Data Index: 1106214 (The Pile)

Max Activating Token Index: 20

Text #14

Max Range: 0.1152. Min Range: -0.1152

Max Act: 0.0942. Min Act: -0.0000

Data Index: 337141 (The Pile)

Max Activating Token Index: 14

Text #15

Max Range: 0.1152. Min Range: -0.1152

Max Act: 0.0942. Min Act: -0.0000

Data Index: 367651 (The Pile)

Max Activating Token Index: 14

Text #16

Max Range: 0.1152. Min Range: -0.1152

Max Act: 0.0927. Min Act: -0.0000

Data Index: 235255 (The Pile)

Max Activating Token Index: 1023

Text #17

Max Range: 0.1152. Min Range: -0.1152

Max Act: 0.0925. Min Act: -0.0000

Data Index: 1184092 (The Pile)

Max Activating Token Index: 15

Text #18

Max Range: 0.1152. Min Range: -0.1152

Max Act: 0.0924. Min Act: -0.0000

Data Index: 72118 (The Pile)

Max Activating Token Index: 42

Text #19

Max Range: 0.1152. Min Range: -0.1152

Max Act: 0.0922. Min Act: -0.0000

Data Index: 1679441 (The Pile)

Max Activating Token Index: 16