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

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

Neuron 2915 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0867. Min Act: -0.0002

Data Index: 1465243 (Python Code)

Max Activating Token Index: 44

Text #1

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0841. Min Act: -0.0002

Data Index: 1545657 (Python Code)

Max Activating Token Index: 6

Text #2

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0851. Min Act: -0.0002

Data Index: 1594360 (Python Code)

Max Activating Token Index: 3

Text #3

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0851. Min Act: -0.0002

Data Index: 1538805 (Python Code)

Max Activating Token Index: 3

Text #4

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0846. Min Act: -0.0002

Data Index: 1522669 (Python Code)

Max Activating Token Index: 3

Text #5

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0833. Min Act: -0.0002

Data Index: 1646323 (Python Code)

Max Activating Token Index: 6

Text #6

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0820. Min Act: -0.0002

Data Index: 1401393 (Python Code)

Max Activating Token Index: 4

Text #7

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0828. Min Act: -0.0002

Data Index: 1589982 (Python Code)

Max Activating Token Index: 10

Text #8

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0820. Min Act: -0.0002

Data Index: 1423013 (Python Code)

Max Activating Token Index: 5

Text #9

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0786. Min Act: -0.0002

Data Index: 1448886 (Python Code)

Max Activating Token Index: 4

Text #10

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0772. Min Act: -0.0002

Data Index: 1567432 (Python Code)

Max Activating Token Index: 8

Text #11

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0770. Min Act: -0.0002

Data Index: 1553946 (Python Code)

Max Activating Token Index: 5

Text #12

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0762. Min Act: -0.0002

Data Index: 1616977 (Python Code)

Max Activating Token Index: 6

Text #13

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0773. Min Act: -0.0002

Data Index: 1573117 (Python Code)

Max Activating Token Index: 4

Text #14

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0762. Min Act: -0.0002

Data Index: 1436146 (Python Code)

Max Activating Token Index: 3

Text #15

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0765. Min Act: -0.0002

Data Index: 1549674 (Python Code)

Max Activating Token Index: 41

Text #16

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0757. Min Act: -0.0002

Data Index: 1608897 (Python Code)

Max Activating Token Index: 7

Text #17

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0747. Min Act: -0.0002

Data Index: 1547400 (Python Code)

Max Activating Token Index: 3

Text #18

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0753. Min Act: -0.0002

Data Index: 1415969 (Python Code)

Max Activating Token Index: 3

Text #19

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0753. Min Act: -0.0002

Data Index: 1392635 (Python Code)

Max Activating Token Index: 3