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

Dataset: The Pile

Neuron 4295 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: 0.1167. Min Range: -0.1167

Max Act: 0.1162. Min Act: -0.0000

Data Index: 465486 (The Pile)

Max Activating Token Index: 3

Text #1

Max Range: 0.1167. Min Range: -0.1167

Max Act: 0.1140. Min Act: -0.0000

Data Index: 440958 (The Pile)

Max Activating Token Index: 1023

Text #2

Max Range: 0.1167. Min Range: -0.1167

Max Act: 0.1167. Min Act: -0.0000

Data Index: 1179956 (The Pile)

Max Activating Token Index: 9

Text #3

Max Range: 0.1167. Min Range: -0.1167

Max Act: 0.1093. Min Act: -0.0000

Data Index: 583543 (The Pile)

Max Activating Token Index: 1023

Text #4

Max Range: 0.1167. Min Range: -0.1167

Max Act: 0.1089. Min Act: -0.0000

Data Index: 323584 (The Pile)

Max Activating Token Index: 1023

Text #5

Max Range: 0.1167. Min Range: -0.1167

Max Act: 0.1073. Min Act: 0.0000

Data Index: 1203696 (The Pile)

Max Activating Token Index: 242

Text #6

Max Range: 0.1167. Min Range: -0.1167

Max Act: 0.1032. Min Act: -0.0000

Data Index: 1571827 (The Pile)

Max Activating Token Index: 9

Text #7

Max Range: 0.1167. Min Range: -0.1167

Max Act: 0.1024. Min Act: 0.0000

Data Index: 115592 (The Pile)

Max Activating Token Index: 2

Text #8

Max Range: 0.1167. Min Range: -0.1167

Max Act: 0.1025. Min Act: 0.0000

Data Index: 210870 (The Pile)

Max Activating Token Index: 4

Text #9

Max Range: 0.1167. Min Range: -0.1167

Max Act: 0.1009. Min Act: -0.0000

Data Index: 1071960 (The Pile)

Max Activating Token Index: 1023

Text #10

Max Range: 0.1167. Min Range: -0.1167

Max Act: 0.1008. Min Act: -0.0000

Data Index: 306862 (The Pile)

Max Activating Token Index: 1023

Text #11

Max Range: 0.1167. Min Range: -0.1167

Max Act: 0.1004. Min Act: -0.0000

Data Index: 1854208 (The Pile)

Max Activating Token Index: 4

Text #12

Max Range: 0.1167. Min Range: -0.1167

Max Act: 0.1002. Min Act: -0.0000

Data Index: 543770 (The Pile)

Max Activating Token Index: 9

Text #13

Max Range: 0.1167. Min Range: -0.1167

Max Act: 0.0997. Min Act: -0.0000

Data Index: 364638 (The Pile)

Max Activating Token Index: 49

Text #14

Max Range: 0.1167. Min Range: -0.1167

Max Act: 0.0996. Min Act: -0.0000

Data Index: 298906 (The Pile)

Max Activating Token Index: 1023

Text #15

Max Range: 0.1167. Min Range: -0.1167

Max Act: 0.1027. Min Act: -0.0000

Data Index: 583443 (The Pile)

Max Activating Token Index: 3

Text #16

Max Range: 0.1167. Min Range: -0.1167

Max Act: 0.0991. Min Act: -0.0000

Data Index: 165877 (The Pile)

Max Activating Token Index: 106

Text #17

Max Range: 0.1167. Min Range: -0.1167

Max Act: 0.0990. Min Act: -0.0000

Data Index: 1348217 (The Pile)

Max Activating Token Index: 3

Text #18

Max Range: 0.1167. Min Range: -0.1167

Max Act: 0.0989. Min Act: -0.0000

Data Index: 735610 (The Pile)

Max Activating Token Index: 5

Text #19

Max Range: 0.1167. Min Range: -0.1167

Max Act: 0.0983. Min Act: -0.0000

Data Index: 810926 (The Pile)

Max Activating Token Index: 7