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

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

Neuron 4553 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: 0.0958. Min Range: -0.0958

Max Act: 0.0958. Min Act: -0.0002

Data Index: 1499181 (Python Code)

Max Activating Token Index: 598

Text #1

Max Range: 0.0958. Min Range: -0.0958

Max Act: 0.0831. Min Act: -0.0002

Data Index: 1398011 (Python Code)

Max Activating Token Index: 233

Text #2

Max Range: 0.0958. Min Range: -0.0958

Max Act: 0.0947. Min Act: -0.0002

Data Index: 1533374 (Python Code)

Max Activating Token Index: 672

Text #3

Max Range: 0.0958. Min Range: -0.0958

Max Act: 0.0896. Min Act: -0.0002

Data Index: 1465336 (Python Code)

Max Activating Token Index: 432

Text #4

Max Range: 0.0958. Min Range: -0.0958

Max Act: 0.0827. Min Act: -0.0002

Data Index: 1401895 (Python Code)

Max Activating Token Index: 158

Text #5

Max Range: 0.0958. Min Range: -0.0958

Max Act: 0.0904. Min Act: -0.0002

Data Index: 1609273 (Python Code)

Max Activating Token Index: 462

Text #6

Max Range: 0.0958. Min Range: -0.0958

Max Act: 0.0848. Min Act: -0.0002

Data Index: 1499683 (Python Code)

Max Activating Token Index: 722

Text #7

Max Range: 0.0958. Min Range: -0.0958

Max Act: 0.0842. Min Act: -0.0002

Data Index: 1418388 (Python Code)

Max Activating Token Index: 353

Text #8

Max Range: 0.0958. Min Range: -0.0958

Max Act: 0.0729. Min Act: -0.0002

Data Index: 1595947 (Python Code)

Max Activating Token Index: 736

Text #9

Max Range: 0.0958. Min Range: -0.0958

Max Act: 0.0843. Min Act: -0.0002

Data Index: 1426304 (Python Code)

Max Activating Token Index: 838

Text #10

Max Range: 0.0958. Min Range: -0.0958

Max Act: 0.0804. Min Act: -0.0002

Data Index: 1449751 (Python Code)

Max Activating Token Index: 365

Text #11

Max Range: 0.0958. Min Range: -0.0958

Max Act: 0.0806. Min Act: -0.0002

Data Index: 1647838 (Python Code)

Max Activating Token Index: 585

Text #12

Max Range: 0.0958. Min Range: -0.0958

Max Act: 0.0767. Min Act: -0.0002

Data Index: 1553737 (Python Code)

Max Activating Token Index: 531

Text #13

Max Range: 0.0958. Min Range: -0.0958

Max Act: 0.0804. Min Act: -0.0002

Data Index: 1502018 (Python Code)

Max Activating Token Index: 22

Text #14

Max Range: 0.0958. Min Range: -0.0958

Max Act: 0.0710. Min Act: -0.0002

Data Index: 1366074 (Python Code)

Max Activating Token Index: 644

Text #15

Max Range: 0.0958. Min Range: -0.0958

Max Act: 0.0743. Min Act: -0.0002

Data Index: 1573576 (Python Code)

Max Activating Token Index: 913

Text #16

Max Range: 0.0958. Min Range: -0.0958

Max Act: 0.0823. Min Act: -0.0002

Data Index: 1562093 (Python Code)

Max Activating Token Index: 645

Text #17

Max Range: 0.0958. Min Range: -0.0958

Max Act: 0.0844. Min Act: -0.0002

Data Index: 1570709 (Python Code)

Max Activating Token Index: 102

Text #18

Max Range: 0.0958. Min Range: -0.0958

Max Act: 0.0760. Min Act: -0.0002

Data Index: 1616072 (Python Code)

Max Activating Token Index: 840

Text #19

Max Range: 0.0958. Min Range: -0.0958

Max Act: 0.0790. Min Act: -0.0002

Data Index: 1377077 (Python Code)

Max Activating Token Index: 472