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

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

Neuron 960 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: 0.1146. Min Range: -0.1146

Max Act: 0.1146. Min Act: -0.0003

Data Index: 1537286 (Python Code)

Max Activating Token Index: 12

Text #1

Max Range: 0.1146. Min Range: -0.1146

Max Act: 0.1043. Min Act: -0.0003

Data Index: 1530983 (Python Code)

Max Activating Token Index: 14

Text #2

Max Range: 0.1146. Min Range: -0.1146

Max Act: 0.1042. Min Act: -0.0003

Data Index: 1466640 (Python Code)

Max Activating Token Index: 13

Text #3

Max Range: 0.1146. Min Range: -0.1146

Max Act: 0.1038. Min Act: -0.0003

Data Index: 1520715 (Python Code)

Max Activating Token Index: 13

Text #4

Max Range: 0.1146. Min Range: -0.1146

Max Act: 0.1013. Min Act: -0.0003

Data Index: 1538691 (Python Code)

Max Activating Token Index: 20

Text #5

Max Range: 0.1146. Min Range: -0.1146

Max Act: 0.0983. Min Act: -0.0003

Data Index: 1557226 (Python Code)

Max Activating Token Index: 1005

Text #6

Max Range: 0.1146. Min Range: -0.1146

Max Act: 0.1014. Min Act: -0.0003

Data Index: 1526256 (Python Code)

Max Activating Token Index: 11

Text #7

Max Range: 0.1146. Min Range: -0.1146

Max Act: 0.1014. Min Act: -0.0003

Data Index: 1421103 (Python Code)

Max Activating Token Index: 11

Text #8

Max Range: 0.1146. Min Range: -0.1146

Max Act: 0.1042. Min Act: -0.0003

Data Index: 1561264 (Python Code)

Max Activating Token Index: 9

Text #9

Max Range: 0.1146. Min Range: -0.1146

Max Act: 0.0995. Min Act: -0.0003

Data Index: 1499149 (Python Code)

Max Activating Token Index: 13

Text #10

Max Range: 0.1146. Min Range: -0.1146

Max Act: 0.0995. Min Act: -0.0004

Data Index: 1414998 (Python Code)

Max Activating Token Index: 13

Text #11

Max Range: 0.1146. Min Range: -0.1146

Max Act: 0.0995. Min Act: -0.0003

Data Index: 1433401 (Python Code)

Max Activating Token Index: 13

Text #12

Max Range: 0.1146. Min Range: -0.1146

Max Act: 0.0972. Min Act: -0.0003

Data Index: 1450174 (Python Code)

Max Activating Token Index: 15

Text #13

Max Range: 0.1146. Min Range: -0.1146

Max Act: 0.0982. Min Act: -0.0003

Data Index: 1474737 (Python Code)

Max Activating Token Index: 12

Text #14

Max Range: 0.1146. Min Range: -0.1146

Max Act: 0.0982. Min Act: -0.0003

Data Index: 1504920 (Python Code)

Max Activating Token Index: 12

Text #15

Max Range: 0.1146. Min Range: -0.1146

Max Act: 0.0982. Min Act: -0.0003

Data Index: 1628160 (Python Code)

Max Activating Token Index: 12

Text #16

Max Range: 0.1146. Min Range: -0.1146

Max Act: 0.0962. Min Act: -0.0003

Data Index: 1379894 (Python Code)

Max Activating Token Index: 15

Text #17

Max Range: 0.1146. Min Range: -0.1146

Max Act: 0.0980. Min Act: -0.0003

Data Index: 1593421 (Python Code)

Max Activating Token Index: 7

Text #18

Max Range: 0.1146. Min Range: -0.1146

Max Act: 0.0980. Min Act: -0.0003

Data Index: 1628040 (Python Code)

Max Activating Token Index: 7

Text #19

Max Range: 0.1146. Min Range: -0.1146

Max Act: 0.0980. Min Act: -0.0003

Data Index: 1546932 (Python Code)

Max Activating Token Index: 7