Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1475 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.2057. Min Range: -0.2057

Max Act: 0.2046. Min Act: -0.0003

Data Index: 1577732 (Python Code)

Max Activating Token Index: 112

Text #1

Max Range: 0.2057. Min Range: -0.2057

Max Act: 0.2057. Min Act: -0.0003

Data Index: 1629081 (Python Code)

Max Activating Token Index: 159

Text #2

Max Range: 0.2057. Min Range: -0.2057

Max Act: 0.1962. Min Act: -0.0003

Data Index: 1574132 (Python Code)

Max Activating Token Index: 188

Text #3

Max Range: 0.2057. Min Range: -0.2057

Max Act: 0.1806. Min Act: -0.0003

Data Index: 1445100 (Python Code)

Max Activating Token Index: 567

Text #4

Max Range: 0.2057. Min Range: -0.2057

Max Act: 0.1938. Min Act: -0.0003

Data Index: 1568037 (Python Code)

Max Activating Token Index: 981

Text #5

Max Range: 0.2057. Min Range: -0.2057

Max Act: 0.1939. Min Act: -0.0003

Data Index: 1504053 (Python Code)

Max Activating Token Index: 561

Text #6

Max Range: 0.2057. Min Range: -0.2057

Max Act: 0.1910. Min Act: -0.0003

Data Index: 1369993 (Python Code)

Max Activating Token Index: 514

Text #7

Max Range: 0.2057. Min Range: -0.2057

Max Act: 0.1787. Min Act: -0.0003

Data Index: 1524695 (Python Code)

Max Activating Token Index: 96

Text #8

Max Range: 0.2057. Min Range: -0.2057

Max Act: 0.1827. Min Act: -0.0003

Data Index: 1468992 (Python Code)

Max Activating Token Index: 834

Text #9

Max Range: 0.2057. Min Range: -0.2057

Max Act: 0.1947. Min Act: -0.0003

Data Index: 1648561 (Python Code)

Max Activating Token Index: 177

Text #10

Max Range: 0.2057. Min Range: -0.2057

Max Act: 0.1926. Min Act: -0.0003

Data Index: 1623738 (Python Code)

Max Activating Token Index: 883

Text #11

Max Range: 0.2057. Min Range: -0.2057

Max Act: 0.1905. Min Act: -0.0004

Data Index: 1371649 (Python Code)

Max Activating Token Index: 696

Text #12

Max Range: 0.2057. Min Range: -0.2057

Max Act: 0.1921. Min Act: -0.0003

Data Index: 1529951 (Python Code)

Max Activating Token Index: 190

Text #13

Max Range: 0.2057. Min Range: -0.2057

Max Act: 0.1851. Min Act: -0.0003

Data Index: 1526025 (Python Code)

Max Activating Token Index: 184

Text #14

Max Range: 0.2057. Min Range: -0.2057

Max Act: 0.1839. Min Act: -0.0003

Data Index: 1615821 (Python Code)

Max Activating Token Index: 706

Text #15

Max Range: 0.2057. Min Range: -0.2057

Max Act: 0.1785. Min Act: -0.0003

Data Index: 1429845 (Python Code)

Max Activating Token Index: 138

Text #16

Max Range: 0.2057. Min Range: -0.2057

Max Act: 0.1722. Min Act: -0.0003

Data Index: 1396290 (Python Code)

Max Activating Token Index: 952

Text #17

Max Range: 0.2057. Min Range: -0.2057

Max Act: 0.1806. Min Act: -0.0003

Data Index: 1448392 (Python Code)

Max Activating Token Index: 144

Text #18

Max Range: 0.2057. Min Range: -0.2057

Max Act: 0.1833. Min Act: -0.0003

Data Index: 1646564 (Python Code)

Max Activating Token Index: 596

Text #19

Max Range: 0.2057. Min Range: -0.2057

Max Act: 0.1798. Min Act: -0.0003

Data Index: 1445699 (Python Code)

Max Activating Token Index: 142