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

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

Neuron 2166 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: 0.0995. Min Range: -0.0995

Max Act: 0.0871. Min Act: -0.0002

Data Index: 1647263 (Python Code)

Max Activating Token Index: 758

Text #1

Max Range: 0.0995. Min Range: -0.0995

Max Act: 0.0995. Min Act: -0.0002

Data Index: 1103991 (C4 (Web Text))

Max Activating Token Index: 16

Text #2

Max Range: 0.0995. Min Range: -0.0995

Max Act: 0.0832. Min Act: -0.0002

Data Index: 1467702 (Python Code)

Max Activating Token Index: 213

Text #3

Max Range: 0.0995. Min Range: -0.0995

Max Act: 0.0931. Min Act: -0.0002

Data Index: 1015790 (C4 (Web Text))

Max Activating Token Index: 239

Text #4

Max Range: 0.0995. Min Range: -0.0995

Max Act: 0.0946. Min Act: -0.0002

Data Index: 1228110 (C4 (Web Text))

Max Activating Token Index: 40

Text #5

Max Range: 0.0995. Min Range: -0.0995

Max Act: 0.0873. Min Act: -0.0002

Data Index: 284383 (C4 (Web Text))

Max Activating Token Index: 800

Text #6

Max Range: 0.0995. Min Range: -0.0995

Max Act: 0.0817. Min Act: -0.0002

Data Index: 489554 (C4 (Web Text))

Max Activating Token Index: 353

Text #7

Max Range: 0.0995. Min Range: -0.0995

Max Act: 0.0897. Min Act: -0.0002

Data Index: 1231801 (C4 (Web Text))

Max Activating Token Index: 97

Text #8

Max Range: 0.0995. Min Range: -0.0995

Max Act: 0.0923. Min Act: -0.0002

Data Index: 1162033 (C4 (Web Text))

Max Activating Token Index: 856

Text #9

Max Range: 0.0995. Min Range: -0.0995

Max Act: 0.0806. Min Act: -0.0002

Data Index: 1095990 (C4 (Web Text))

Max Activating Token Index: 47

Text #10

Max Range: 0.0995. Min Range: -0.0995

Max Act: 0.0825. Min Act: -0.0002

Data Index: 1559953 (Python Code)

Max Activating Token Index: 771

Text #11

Max Range: 0.0995. Min Range: -0.0995

Max Act: 0.0919. Min Act: -0.0002

Data Index: 1413124 (Python Code)

Max Activating Token Index: 910

Text #12

Max Range: 0.0995. Min Range: -0.0995

Max Act: 0.0876. Min Act: -0.0002

Data Index: 1491308 (Python Code)

Max Activating Token Index: 430

Text #13

Max Range: 0.0995. Min Range: -0.0995

Max Act: 0.0925. Min Act: -0.0002

Data Index: 1387686 (Python Code)

Max Activating Token Index: 172

Text #14

Max Range: 0.0995. Min Range: -0.0995

Max Act: 0.0832. Min Act: -0.0002

Data Index: 61168 (C4 (Web Text))

Max Activating Token Index: 349

Text #15

Max Range: 0.0995. Min Range: -0.0995

Max Act: 0.0896. Min Act: -0.0002

Data Index: 240467 (C4 (Web Text))

Max Activating Token Index: 750

Text #16

Max Range: 0.0995. Min Range: -0.0995

Max Act: 0.0791. Min Act: -0.0002

Data Index: 910652 (C4 (Web Text))

Max Activating Token Index: 24

Text #17

Max Range: 0.0995. Min Range: -0.0995

Max Act: 0.0823. Min Act: -0.0002

Data Index: 1626328 (Python Code)

Max Activating Token Index: 97

Text #18

Max Range: 0.0995. Min Range: -0.0995

Max Act: 0.0917. Min Act: -0.0002

Data Index: 1640243 (Python Code)

Max Activating Token Index: 674

Text #19

Max Range: 0.0995. Min Range: -0.0995

Max Act: 0.0805. Min Act: -0.0002

Data Index: 208544 (C4 (Web Text))

Max Activating Token Index: 240