Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1805 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.5788. Min Range: -0.5788

Max Act: 0.5788. Min Act: -0.0002

Data Index: 1513993 (Python Code)

Max Activating Token Index: 1

Text #1

Max Range: 0.5788. Min Range: -0.5788

Max Act: 0.5788. Min Act: -0.0002

Data Index: 1535552 (Python Code)

Max Activating Token Index: 1

Text #2

Max Range: 0.5788. Min Range: -0.5788

Max Act: 0.5685. Min Act: -0.0002

Data Index: 1414228 (Python Code)

Max Activating Token Index: 1

Text #3

Max Range: 0.5788. Min Range: -0.5788

Max Act: 0.5664. Min Act: -0.0002

Data Index: 1546997 (Python Code)

Max Activating Token Index: 1

Text #4

Max Range: 0.5788. Min Range: -0.5788

Max Act: 0.5664. Min Act: -0.0002

Data Index: 1362830 (Python Code)

Max Activating Token Index: 1

Text #5

Max Range: 0.5788. Min Range: -0.5788

Max Act: 0.5664. Min Act: -0.0002

Data Index: 1542954 (Python Code)

Max Activating Token Index: 1

Text #6

Max Range: 0.5788. Min Range: -0.5788

Max Act: 0.5664. Min Act: -0.0002

Data Index: 1538233 (Python Code)

Max Activating Token Index: 1

Text #7

Max Range: 0.5788. Min Range: -0.5788

Max Act: 0.5664. Min Act: -0.0002

Data Index: 1392952 (Python Code)

Max Activating Token Index: 1

Text #8

Max Range: 0.5788. Min Range: -0.5788

Max Act: 0.5664. Min Act: -0.0002

Data Index: 1515878 (Python Code)

Max Activating Token Index: 1

Text #9

Max Range: 0.5788. Min Range: -0.5788

Max Act: 0.4775. Min Act: -0.0002

Data Index: 1445696 (Python Code)

Max Activating Token Index: 1

Text #10

Max Range: 0.5788. Min Range: -0.5788

Max Act: 0.4775. Min Act: -0.0002

Data Index: 1524225 (Python Code)

Max Activating Token Index: 1

Text #11

Max Range: 0.5788. Min Range: -0.5788

Max Act: 0.4775. Min Act: -0.0002

Data Index: 1495990 (Python Code)

Max Activating Token Index: 1

Text #12

Max Range: 0.5788. Min Range: -0.5788

Max Act: 0.4775. Min Act: -0.0002

Data Index: 1620659 (Python Code)

Max Activating Token Index: 1

Text #13

Max Range: 0.5788. Min Range: -0.5788

Max Act: 0.4775. Min Act: -0.0002

Data Index: 1368271 (Python Code)

Max Activating Token Index: 1

Text #14

Max Range: 0.5788. Min Range: -0.5788

Max Act: 0.4708. Min Act: -0.0002

Data Index: 1432545 (Python Code)

Max Activating Token Index: 1

Text #15

Max Range: 0.5788. Min Range: -0.5788

Max Act: 0.4708. Min Act: -0.0002

Data Index: 1389270 (Python Code)

Max Activating Token Index: 1

Text #16

Max Range: 0.5788. Min Range: -0.5788

Max Act: 0.4708. Min Act: -0.0002

Data Index: 1427078 (Python Code)

Max Activating Token Index: 1

Text #17

Max Range: 0.5788. Min Range: -0.5788

Max Act: 0.4708. Min Act: -0.0002

Data Index: 1451272 (Python Code)

Max Activating Token Index: 1

Text #18

Max Range: 0.5788. Min Range: -0.5788

Max Act: 0.4708. Min Act: -0.0002

Data Index: 1459555 (Python Code)

Max Activating Token Index: 1

Text #19

Max Range: 0.5788. Min Range: -0.5788

Max Act: 0.4708. Min Act: -0.0002

Data Index: 1444817 (Python Code)

Max Activating Token Index: 1