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

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

Neuron 372 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: 1.0208. Min Range: -1.0208

Max Act: 1.0208. Min Act: -0.0002

Data Index: 868901 (C4 (Web Text))

Max Activating Token Index: 998

Text #1

Max Range: 1.0208. Min Range: -1.0208

Max Act: 0.9062. Min Act: -0.0002

Data Index: 196389 (C4 (Web Text))

Max Activating Token Index: 919

Text #2

Max Range: 1.0208. Min Range: -1.0208

Max Act: 0.8629. Min Act: -0.0002

Data Index: 1630850 (Python Code)

Max Activating Token Index: 746

Text #3

Max Range: 1.0208. Min Range: -1.0208

Max Act: 0.8265. Min Act: -0.0002

Data Index: 1396176 (Python Code)

Max Activating Token Index: 754

Text #4

Max Range: 1.0208. Min Range: -1.0208

Max Act: 0.9874. Min Act: -0.0002

Data Index: 1552005 (Python Code)

Max Activating Token Index: 945

Text #5

Max Range: 1.0208. Min Range: -1.0208

Max Act: 1.0094. Min Act: -0.0002

Data Index: 265048 (C4 (Web Text))

Max Activating Token Index: 914

Text #6

Max Range: 1.0208. Min Range: -1.0208

Max Act: 0.8131. Min Act: -0.0002

Data Index: 1308210 (C4 (Web Text))

Max Activating Token Index: 923

Text #7

Max Range: 1.0208. Min Range: -1.0208

Max Act: 0.6247. Min Act: -0.0002

Data Index: 1067131 (C4 (Web Text))

Max Activating Token Index: 521

Text #8

Max Range: 1.0208. Min Range: -1.0208

Max Act: 0.7733. Min Act: -0.0002

Data Index: 1455007 (Python Code)

Max Activating Token Index: 706

Text #9

Max Range: 1.0208. Min Range: -1.0208

Max Act: 0.8216. Min Act: -0.0002

Data Index: 1376569 (Python Code)

Max Activating Token Index: 387

Text #10

Max Range: 1.0208. Min Range: -1.0208

Max Act: 0.6938. Min Act: -0.0002

Data Index: 353540 (C4 (Web Text))

Max Activating Token Index: 274

Text #11

Max Range: 1.0208. Min Range: -1.0208

Max Act: 0.7693. Min Act: -0.0002

Data Index: 15004 (C4 (Web Text))

Max Activating Token Index: 817

Text #12

Max Range: 1.0208. Min Range: -1.0208

Max Act: 0.7089. Min Act: -0.0002

Data Index: 1314095 (C4 (Web Text))

Max Activating Token Index: 504

Text #13

Max Range: 1.0208. Min Range: -1.0208

Max Act: 0.7986. Min Act: -0.0002

Data Index: 840148 (C4 (Web Text))

Max Activating Token Index: 956

Text #14

Max Range: 1.0208. Min Range: -1.0208

Max Act: 0.9005. Min Act: -0.0002

Data Index: 1361783 (Python Code)

Max Activating Token Index: 297

Text #15

Max Range: 1.0208. Min Range: -1.0208

Max Act: 0.7766. Min Act: -0.0002

Data Index: 1362805 (Python Code)

Max Activating Token Index: 863

Text #16

Max Range: 1.0208. Min Range: -1.0208

Max Act: 0.8935. Min Act: -0.0002

Data Index: 1300004 (C4 (Web Text))

Max Activating Token Index: 122

Text #17

Max Range: 1.0208. Min Range: -1.0208

Max Act: 0.8255. Min Act: -0.0002

Data Index: 937074 (C4 (Web Text))

Max Activating Token Index: 748

Text #18

Max Range: 1.0208. Min Range: -1.0208

Max Act: 0.7635. Min Act: -0.0002

Data Index: 1529497 (Python Code)

Max Activating Token Index: 475

Text #19

Max Range: 1.0208. Min Range: -1.0208

Max Act: 0.8121. Min Act: -0.0002

Data Index: 1494001 (Python Code)

Max Activating Token Index: 103