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

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

Neuron 1069 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: 0.2563. Min Range: -0.2563

Max Act: 0.2563. Min Act: -0.0000

Data Index: 324933 (C4 (Web Text))

Max Activating Token Index: 268

Text #1

Max Range: 0.2563. Min Range: -0.2563

Max Act: 0.2307. Min Act: -0.0000

Data Index: 870086 (C4 (Web Text))

Max Activating Token Index: 270

Text #2

Max Range: 0.2563. Min Range: -0.2563

Max Act: 0.2361. Min Act: -0.0000

Data Index: 1280114 (C4 (Web Text))

Max Activating Token Index: 432

Text #3

Max Range: 0.2563. Min Range: -0.2563

Max Act: 0.2046. Min Act: -0.0000

Data Index: 1188793 (C4 (Web Text))

Max Activating Token Index: 815

Text #4

Max Range: 0.2563. Min Range: -0.2563

Max Act: 0.2181. Min Act: -0.0000

Data Index: 1275405 (C4 (Web Text))

Max Activating Token Index: 48

Text #5

Max Range: 0.2563. Min Range: -0.2563

Max Act: 0.1910. Min Act: -0.0000

Data Index: 169403 (C4 (Web Text))

Max Activating Token Index: 756

Text #6

Max Range: 0.2563. Min Range: -0.2563

Max Act: 0.1973. Min Act: -0.0000

Data Index: 986252 (C4 (Web Text))

Max Activating Token Index: 1000

Text #7

Max Range: 0.2563. Min Range: -0.2563

Max Act: 0.2012. Min Act: -0.0000

Data Index: 123237 (C4 (Web Text))

Max Activating Token Index: 84

Text #8

Max Range: 0.2563. Min Range: -0.2563

Max Act: 0.1999. Min Act: -0.0000

Data Index: 345752 (C4 (Web Text))

Max Activating Token Index: 1017

Text #9

Max Range: 0.2563. Min Range: -0.2563

Max Act: 0.1957. Min Act: -0.0000

Data Index: 1290404 (C4 (Web Text))

Max Activating Token Index: 150

Text #10

Max Range: 0.2563. Min Range: -0.2563

Max Act: 0.1845. Min Act: -0.0000

Data Index: 1113762 (C4 (Web Text))

Max Activating Token Index: 220

Text #11

Max Range: 0.2563. Min Range: -0.2563

Max Act: 0.1873. Min Act: -0.0000

Data Index: 847164 (C4 (Web Text))

Max Activating Token Index: 522

Text #12

Max Range: 0.2563. Min Range: -0.2563

Max Act: 0.1929. Min Act: -0.0000

Data Index: 218476 (C4 (Web Text))

Max Activating Token Index: 763

Text #13

Max Range: 0.2563. Min Range: -0.2563

Max Act: 0.1775. Min Act: -0.0000

Data Index: 836758 (C4 (Web Text))

Max Activating Token Index: 508

Text #14

Max Range: 0.2563. Min Range: -0.2563

Max Act: 0.1843. Min Act: -0.0000

Data Index: 1044714 (C4 (Web Text))

Max Activating Token Index: 267

Text #15

Max Range: 0.2563. Min Range: -0.2563

Max Act: 0.1798. Min Act: -0.0000

Data Index: 236966 (C4 (Web Text))

Max Activating Token Index: 285

Text #16

Max Range: 0.2563. Min Range: -0.2563

Max Act: 0.1680. Min Act: -0.0000

Data Index: 840447 (C4 (Web Text))

Max Activating Token Index: 630

Text #17

Max Range: 0.2563. Min Range: -0.2563

Max Act: 0.1719. Min Act: -0.0000

Data Index: 723632 (C4 (Web Text))

Max Activating Token Index: 439

Text #18

Max Range: 0.2563. Min Range: -0.2563

Max Act: 0.1825. Min Act: -0.0000

Data Index: 313082 (C4 (Web Text))

Max Activating Token Index: 80

Text #19

Max Range: 0.2563. Min Range: -0.2563

Max Act: 0.1631. Min Act: -0.0000

Data Index: 108811 (C4 (Web Text))

Max Activating Token Index: 829