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

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 3310 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1134. Min Range: -0.1134

Max Act: 0.1064. Min Act: -0.0002

Data Index: 1545470 (Python Code)

Max Activating Token Index: 310

Text #1

Max Range: 0.1134. Min Range: -0.1134

Max Act: 0.1058. Min Act: -0.0002

Data Index: 1527073 (Python Code)

Max Activating Token Index: 20

Text #2

Max Range: 0.1134. Min Range: -0.1134

Max Act: 0.1134. Min Act: -0.0002

Data Index: 1623804 (Python Code)

Max Activating Token Index: 18

Text #3

Max Range: 0.1134. Min Range: -0.1134

Max Act: 0.1094. Min Act: -0.0002

Data Index: 1437751 (Python Code)

Max Activating Token Index: 7

Text #4

Max Range: 0.1134. Min Range: -0.1134

Max Act: 0.1070. Min Act: -0.0002

Data Index: 1415497 (Python Code)

Max Activating Token Index: 46

Text #5

Max Range: 0.1134. Min Range: -0.1134

Max Act: 0.1093. Min Act: -0.0002

Data Index: 1405332 (Python Code)

Max Activating Token Index: 17

Text #6

Max Range: 0.1134. Min Range: -0.1134

Max Act: 0.1025. Min Act: -0.0002

Data Index: 1525964 (Python Code)

Max Activating Token Index: 8

Text #7

Max Range: 0.1134. Min Range: -0.1134

Max Act: 0.1025. Min Act: -0.0002

Data Index: 1399657 (Python Code)

Max Activating Token Index: 8

Text #8

Max Range: 0.1134. Min Range: -0.1134

Max Act: 0.1033. Min Act: -0.0002

Data Index: 1606632 (Python Code)

Max Activating Token Index: 101

Text #9

Max Range: 0.1134. Min Range: -0.1134

Max Act: 0.1027. Min Act: -0.0002

Data Index: 1384181 (Python Code)

Max Activating Token Index: 52

Text #10

Max Range: 0.1134. Min Range: -0.1134

Max Act: 0.1029. Min Act: -0.0002

Data Index: 1380599 (Python Code)

Max Activating Token Index: 17

Text #11

Max Range: 0.1134. Min Range: -0.1134

Max Act: 0.1060. Min Act: -0.0002

Data Index: 1651030 (Python Code)

Max Activating Token Index: 15

Text #12

Max Range: 0.1134. Min Range: -0.1134

Max Act: 0.0966. Min Act: -0.0002

Data Index: 1551101 (Python Code)

Max Activating Token Index: 20

Text #13

Max Range: 0.1134. Min Range: -0.1134

Max Act: 0.0993. Min Act: -0.0002

Data Index: 1395556 (Python Code)

Max Activating Token Index: 140

Text #14

Max Range: 0.1134. Min Range: -0.1134

Max Act: 0.0991. Min Act: -0.0002

Data Index: 1459567 (Python Code)

Max Activating Token Index: 503

Text #15

Max Range: 0.1134. Min Range: -0.1134

Max Act: 0.1024. Min Act: -0.0002

Data Index: 1381130 (Python Code)

Max Activating Token Index: 73

Text #16

Max Range: 0.1134. Min Range: -0.1134

Max Act: 0.0971. Min Act: -0.0002

Data Index: 1416227 (Python Code)

Max Activating Token Index: 26

Text #17

Max Range: 0.1134. Min Range: -0.1134

Max Act: 0.1004. Min Act: -0.0002

Data Index: 1578646 (Python Code)

Max Activating Token Index: 20

Text #18

Max Range: 0.1134. Min Range: -0.1134

Max Act: 0.0997. Min Act: -0.0002

Data Index: 1564713 (Python Code)

Max Activating Token Index: 147

Text #19

Max Range: 0.1134. Min Range: -0.1134

Max Act: 0.1033. Min Act: -0.0002

Data Index: 1627631 (Python Code)

Max Activating Token Index: 114