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

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

Neuron 324 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7158. Min Range: -0.7158

Max Act: 0.6993. Min Act: -0.0000

Data Index: 1365755 (Python Code)

Max Activating Token Index: 816

Text #1

Max Range: 0.7158. Min Range: -0.7158

Max Act: 0.7158. Min Act: -0.0000

Data Index: 1633381 (Python Code)

Max Activating Token Index: 84

Text #2

Max Range: 0.7158. Min Range: -0.7158

Max Act: 0.6960. Min Act: -0.0000

Data Index: 1541143 (Python Code)

Max Activating Token Index: 982

Text #3

Max Range: 0.7158. Min Range: -0.7158

Max Act: 0.7041. Min Act: -0.0000

Data Index: 1396186 (Python Code)

Max Activating Token Index: 650

Text #4

Max Range: 0.7158. Min Range: -0.7158

Max Act: 0.6629. Min Act: -0.0000

Data Index: 1415063 (Python Code)

Max Activating Token Index: 217

Text #5

Max Range: 0.7158. Min Range: -0.7158

Max Act: 0.6798. Min Act: -0.0000

Data Index: 931152 (C4 (Web Text))

Max Activating Token Index: 102

Text #6

Max Range: 0.7158. Min Range: -0.7158

Max Act: 0.6501. Min Act: -0.0000

Data Index: 1553672 (Python Code)

Max Activating Token Index: 97

Text #7

Max Range: 0.7158. Min Range: -0.7158

Max Act: 0.6709. Min Act: -0.0000

Data Index: 1646258 (Python Code)

Max Activating Token Index: 465

Text #8

Max Range: 0.7158. Min Range: -0.7158

Max Act: 0.6298. Min Act: -0.0000

Data Index: 1478584 (Python Code)

Max Activating Token Index: 785

Text #9

Max Range: 0.7158. Min Range: -0.7158

Max Act: 0.6356. Min Act: -0.0000

Data Index: 1620448 (Python Code)

Max Activating Token Index: 111

Text #10

Max Range: 0.7158. Min Range: -0.7158

Max Act: 0.6559. Min Act: -0.0000

Data Index: 1503094 (Python Code)

Max Activating Token Index: 684

Text #11

Max Range: 0.7158. Min Range: -0.7158

Max Act: 0.6137. Min Act: -0.0000

Data Index: 1509764 (Python Code)

Max Activating Token Index: 545

Text #12

Max Range: 0.7158. Min Range: -0.7158

Max Act: 0.6252. Min Act: -0.0000

Data Index: 1569397 (Python Code)

Max Activating Token Index: 340

Text #13

Max Range: 0.7158. Min Range: -0.7158

Max Act: 0.6198. Min Act: -0.0000

Data Index: 1458813 (Python Code)

Max Activating Token Index: 422

Text #14

Max Range: 0.7158. Min Range: -0.7158

Max Act: 0.6020. Min Act: -0.0000

Data Index: 1376788 (Python Code)

Max Activating Token Index: 501

Text #15

Max Range: 0.7158. Min Range: -0.7158

Max Act: 0.6236. Min Act: -0.0000

Data Index: 1618788 (Python Code)

Max Activating Token Index: 66

Text #16

Max Range: 0.7158. Min Range: -0.7158

Max Act: 0.5991. Min Act: -0.0000

Data Index: 1519800 (Python Code)

Max Activating Token Index: 107

Text #17

Max Range: 0.7158. Min Range: -0.7158

Max Act: 0.5928. Min Act: -0.0000

Data Index: 1362868 (Python Code)

Max Activating Token Index: 556

Text #18

Max Range: 0.7158. Min Range: -0.7158

Max Act: 0.5716. Min Act: -0.0000

Data Index: 1619324 (Python Code)

Max Activating Token Index: 94

Text #19

Max Range: 0.7158. Min Range: -0.7158

Max Act: 0.5912. Min Act: -0.0000

Data Index: 1461146 (Python Code)

Max Activating Token Index: 405