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

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

Neuron 1237 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.8717. Min Range: -2.8717

Max Act: 2.8717. Min Act: -0.0000

Data Index: 1416083 (Python Code)

Max Activating Token Index: 306

Text #1

Max Range: 2.8717. Min Range: -2.8717

Max Act: 2.2290. Min Act: -0.0000

Data Index: 1559584 (Python Code)

Max Activating Token Index: 830

Text #2

Max Range: 2.8717. Min Range: -2.8717

Max Act: 2.6938. Min Act: -0.0000

Data Index: 1618993 (Python Code)

Max Activating Token Index: 531

Text #3

Max Range: 2.8717. Min Range: -2.8717

Max Act: 2.2276. Min Act: -0.0000

Data Index: 1395744 (Python Code)

Max Activating Token Index: 599

Text #4

Max Range: 2.8717. Min Range: -2.8717

Max Act: 2.2037. Min Act: -0.0000

Data Index: 1470967 (Python Code)

Max Activating Token Index: 23

Text #5

Max Range: 2.8717. Min Range: -2.8717

Max Act: 2.1875. Min Act: -0.0000

Data Index: 1449138 (Python Code)

Max Activating Token Index: 960

Text #6

Max Range: 2.8717. Min Range: -2.8717

Max Act: 2.1685. Min Act: -0.0000

Data Index: 1618945 (Python Code)

Max Activating Token Index: 382

Text #7

Max Range: 2.8717. Min Range: -2.8717

Max Act: 2.1190. Min Act: -0.0000

Data Index: 1627307 (Python Code)

Max Activating Token Index: 177

Text #8

Max Range: 2.8717. Min Range: -2.8717

Max Act: 2.0944. Min Act: -0.0000

Data Index: 1455993 (Python Code)

Max Activating Token Index: 46

Text #9

Max Range: 2.8717. Min Range: -2.8717

Max Act: 2.0636. Min Act: -0.0000

Data Index: 1482378 (Python Code)

Max Activating Token Index: 141

Text #10

Max Range: 2.8717. Min Range: -2.8717

Max Act: 1.9387. Min Act: -0.0000

Data Index: 1499975 (Python Code)

Max Activating Token Index: 885

Text #11

Max Range: 2.8717. Min Range: -2.8717

Max Act: 1.9076. Min Act: -0.0000

Data Index: 1477931 (Python Code)

Max Activating Token Index: 789

Text #12

Max Range: 2.8717. Min Range: -2.8717

Max Act: 1.9675. Min Act: -0.0000

Data Index: 1591863 (Python Code)

Max Activating Token Index: 909

Text #13

Max Range: 2.8717. Min Range: -2.8717

Max Act: 1.9498. Min Act: -0.0000

Data Index: 1481147 (Python Code)

Max Activating Token Index: 172

Text #14

Max Range: 2.8717. Min Range: -2.8717

Max Act: 1.8808. Min Act: -0.0000

Data Index: 1528560 (Python Code)

Max Activating Token Index: 53

Text #15

Max Range: 2.8717. Min Range: -2.8717

Max Act: 1.7761. Min Act: -0.0000

Data Index: 1551114 (Python Code)

Max Activating Token Index: 740

Text #16

Max Range: 2.8717. Min Range: -2.8717

Max Act: 1.7609. Min Act: -0.0000

Data Index: 1389455 (Python Code)

Max Activating Token Index: 457

Text #17

Max Range: 2.8717. Min Range: -2.8717

Max Act: 1.8421. Min Act: -0.0000

Data Index: 1435837 (Python Code)

Max Activating Token Index: 993

Text #18

Max Range: 2.8717. Min Range: -2.8717

Max Act: 1.7946. Min Act: -0.0000

Data Index: 1625400 (Python Code)

Max Activating Token Index: 28

Text #19

Max Range: 2.8717. Min Range: -2.8717

Max Act: 1.7679. Min Act: -0.0000

Data Index: 1407454 (Python Code)

Max Activating Token Index: 85