Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4120 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.1024. Min Act: -0.0002

Data Index: 1636327 (Python Code)

Max Activating Token Index: 297

Text #1

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0915. Min Act: -0.0002

Data Index: 1627061 (Python Code)

Max Activating Token Index: 196

Text #2

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0795. Min Act: -0.0002

Data Index: 1467521 (Python Code)

Max Activating Token Index: 402

Text #3

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0817. Min Act: -0.0002

Data Index: 1368740 (Python Code)

Max Activating Token Index: 640

Text #4

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0900. Min Act: -0.0002

Data Index: 1478933 (Python Code)

Max Activating Token Index: 165

Text #5

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0842. Min Act: -0.0002

Data Index: 1427200 (Python Code)

Max Activating Token Index: 104

Text #6

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0701. Min Act: -0.0002

Data Index: 1553819 (Python Code)

Max Activating Token Index: 211

Text #7

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0917. Min Act: -0.0002

Data Index: 1547506 (Python Code)

Max Activating Token Index: 285

Text #8

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0846. Min Act: -0.0002

Data Index: 1489666 (Python Code)

Max Activating Token Index: 35

Text #9

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0777. Min Act: -0.0002

Data Index: 1448232 (Python Code)

Max Activating Token Index: 473

Text #10

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0831. Min Act: -0.0002

Data Index: 1501615 (Python Code)

Max Activating Token Index: 226

Text #11

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0801. Min Act: -0.0002

Data Index: 1406885 (Python Code)

Max Activating Token Index: 52

Text #12

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0826. Min Act: -0.0002

Data Index: 1621591 (Python Code)

Max Activating Token Index: 16

Text #13

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0658. Min Act: -0.0002

Data Index: 1382673 (Python Code)

Max Activating Token Index: 75

Text #14

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0820. Min Act: -0.0002

Data Index: 1495857 (Python Code)

Max Activating Token Index: 123

Text #15

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0783. Min Act: -0.0002

Data Index: 1453446 (Python Code)

Max Activating Token Index: 29

Text #16

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0792. Min Act: -0.0002

Data Index: 1440679 (Python Code)

Max Activating Token Index: 224

Text #17

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0783. Min Act: -0.0002

Data Index: 1432375 (Python Code)

Max Activating Token Index: 58

Text #18

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0780. Min Act: -0.0002

Data Index: 1473417 (Python Code)

Max Activating Token Index: 690

Text #19

Max Range: 0.1024. Min Range: -0.1024

Max Act: 0.0745. Min Act: -0.0002

Data Index: 1374674 (Python Code)

Max Activating Token Index: 281