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

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

Neuron 4257 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0069. Min Act: -0.0002

Data Index: 1589959 (Python Code)

Max Activating Token Index: 176

Text #1

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0070. Min Act: -0.0002

Data Index: 1383563 (Python Code)

Max Activating Token Index: 12

Text #2

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0068. Min Act: -0.0002

Data Index: 1643959 (Python Code)

Max Activating Token Index: 155

Text #3

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0068. Min Act: -0.0002

Data Index: 1546329 (Python Code)

Max Activating Token Index: 24

Text #4

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0068. Min Act: -0.0002

Data Index: 312809 (C4 (Web Text))

Max Activating Token Index: 54

Text #5

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0066. Min Act: -0.0001

Data Index: 1216761 (C4 (Web Text))

Max Activating Token Index: 28

Text #6

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0067. Min Act: -0.0002

Data Index: 1604503 (Python Code)

Max Activating Token Index: 11

Text #7

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0065. Min Act: -0.0002

Data Index: 1559234 (Python Code)

Max Activating Token Index: 85

Text #8

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0065. Min Act: -0.0002

Data Index: 1581704 (Python Code)

Max Activating Token Index: 49

Text #9

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0065. Min Act: -0.0002

Data Index: 1465911 (Python Code)

Max Activating Token Index: 13

Text #10

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0065. Min Act: -0.0002

Data Index: 1369061 (Python Code)

Max Activating Token Index: 14

Text #11

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0065. Min Act: -0.0001

Data Index: 102876 (C4 (Web Text))

Max Activating Token Index: 36

Text #12

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0064. Min Act: -0.0002

Data Index: 1498543 (Python Code)

Max Activating Token Index: 29

Text #13

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0064. Min Act: -0.0002

Data Index: 1377057 (Python Code)

Max Activating Token Index: 34

Text #14

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0063. Min Act: -0.0002

Data Index: 1523370 (Python Code)

Max Activating Token Index: 143

Text #15

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0062. Min Act: -0.0002

Data Index: 882867 (C4 (Web Text))

Max Activating Token Index: 39

Text #16

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0063. Min Act: -0.0001

Data Index: 381949 (C4 (Web Text))

Max Activating Token Index: 65

Text #17

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0061. Min Act: -0.0002

Data Index: 1494410 (Python Code)

Max Activating Token Index: 108

Text #18

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0062. Min Act: -0.0002

Data Index: 1491531 (Python Code)

Max Activating Token Index: 73

Text #19

Max Range: 0.0070. Min Range: -0.0070

Max Act: 0.0062. Min Act: -0.0002

Data Index: 1567735 (Python Code)

Max Activating Token Index: 113