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

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

Neuron 2355 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: 0.0982. Min Range: -0.0982

Max Act: 0.0982. Min Act: -0.0002

Data Index: 1527431 (Python Code)

Max Activating Token Index: 65

Text #1

Max Range: 0.0982. Min Range: -0.0982

Max Act: 0.0957. Min Act: -0.0002

Data Index: 1444029 (Python Code)

Max Activating Token Index: 101

Text #2

Max Range: 0.0982. Min Range: -0.0982

Max Act: 0.0978. Min Act: -0.0002

Data Index: 1401418 (Python Code)

Max Activating Token Index: 182

Text #3

Max Range: 0.0982. Min Range: -0.0982

Max Act: 0.0952. Min Act: -0.0002

Data Index: 1615876 (Python Code)

Max Activating Token Index: 49

Text #4

Max Range: 0.0982. Min Range: -0.0982

Max Act: 0.0936. Min Act: -0.0002

Data Index: 1640592 (Python Code)

Max Activating Token Index: 55

Text #5

Max Range: 0.0982. Min Range: -0.0982

Max Act: 0.0910. Min Act: -0.0002

Data Index: 1600075 (Python Code)

Max Activating Token Index: 188

Text #6

Max Range: 0.0982. Min Range: -0.0982

Max Act: 0.0868. Min Act: -0.0002

Data Index: 1402749 (Python Code)

Max Activating Token Index: 114

Text #7

Max Range: 0.0982. Min Range: -0.0982

Max Act: 0.0871. Min Act: -0.0002

Data Index: 1394495 (Python Code)

Max Activating Token Index: 86

Text #8

Max Range: 0.0982. Min Range: -0.0982

Max Act: 0.0840. Min Act: -0.0002

Data Index: 1394776 (Python Code)

Max Activating Token Index: 46

Text #9

Max Range: 0.0982. Min Range: -0.0982

Max Act: 0.0836. Min Act: -0.0002

Data Index: 1516260 (Python Code)

Max Activating Token Index: 144

Text #10

Max Range: 0.0982. Min Range: -0.0982

Max Act: 0.0803. Min Act: -0.0002

Data Index: 1371952 (Python Code)

Max Activating Token Index: 114

Text #11

Max Range: 0.0982. Min Range: -0.0982

Max Act: 0.0830. Min Act: -0.0002

Data Index: 1627491 (Python Code)

Max Activating Token Index: 52

Text #12

Max Range: 0.0982. Min Range: -0.0982

Max Act: 0.0794. Min Act: -0.0002

Data Index: 1451123 (Python Code)

Max Activating Token Index: 49

Text #13

Max Range: 0.0982. Min Range: -0.0982

Max Act: 0.0791. Min Act: -0.0002

Data Index: 1524523 (Python Code)

Max Activating Token Index: 82

Text #14

Max Range: 0.0982. Min Range: -0.0982

Max Act: 0.0769. Min Act: -0.0002

Data Index: 1449924 (Python Code)

Max Activating Token Index: 33

Text #15

Max Range: 0.0982. Min Range: -0.0982

Max Act: 0.0769. Min Act: -0.0002

Data Index: 1391082 (Python Code)

Max Activating Token Index: 60

Text #16

Max Range: 0.0982. Min Range: -0.0982

Max Act: 0.0774. Min Act: -0.0002

Data Index: 1496024 (Python Code)

Max Activating Token Index: 113

Text #17

Max Range: 0.0982. Min Range: -0.0982

Max Act: 0.0779. Min Act: -0.0002

Data Index: 1549555 (Python Code)

Max Activating Token Index: 241

Text #18

Max Range: 0.0982. Min Range: -0.0982

Max Act: 0.0767. Min Act: -0.0002

Data Index: 1507783 (Python Code)

Max Activating Token Index: 173

Text #19

Max Range: 0.0982. Min Range: -0.0982

Max Act: 0.0760. Min Act: -0.0002

Data Index: 1451964 (Python Code)

Max Activating Token Index: 69