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

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

Neuron 2709 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: 0.1016. Min Range: -0.1016

Max Act: 0.0929. Min Act: -0.0000

Data Index: 1477074 (Python Code)

Max Activating Token Index: 653

Text #1

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0857. Min Act: -0.0000

Data Index: 1343951 (C4 (Web Text))

Max Activating Token Index: 830

Text #2

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0855. Min Act: -0.0000

Data Index: 693046 (C4 (Web Text))

Max Activating Token Index: 53

Text #3

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0876. Min Act: -0.0000

Data Index: 1367005 (Python Code)

Max Activating Token Index: 399

Text #4

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.1016. Min Act: -0.0000

Data Index: 708903 (C4 (Web Text))

Max Activating Token Index: 340

Text #5

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0803. Min Act: -0.0000

Data Index: 396999 (C4 (Web Text))

Max Activating Token Index: 810

Text #6

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0881. Min Act: -0.0000

Data Index: 1430230 (Python Code)

Max Activating Token Index: 60

Text #7

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0858. Min Act: -0.0000

Data Index: 675202 (C4 (Web Text))

Max Activating Token Index: 60

Text #8

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0775. Min Act: -0.0000

Data Index: 1038480 (C4 (Web Text))

Max Activating Token Index: 207

Text #9

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0826. Min Act: -0.0000

Data Index: 207301 (C4 (Web Text))

Max Activating Token Index: 282

Text #10

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0809. Min Act: -0.0000

Data Index: 215591 (C4 (Web Text))

Max Activating Token Index: 110

Text #11

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0826. Min Act: -0.0000

Data Index: 1616847 (Python Code)

Max Activating Token Index: 848

Text #12

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0786. Min Act: -0.0000

Data Index: 274756 (C4 (Web Text))

Max Activating Token Index: 396

Text #13

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0786. Min Act: -0.0000

Data Index: 954585 (C4 (Web Text))

Max Activating Token Index: 762

Text #14

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0753. Min Act: -0.0000

Data Index: 1388958 (Python Code)

Max Activating Token Index: 932

Text #15

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0774. Min Act: -0.0000

Data Index: 623311 (C4 (Web Text))

Max Activating Token Index: 918

Text #16

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0805. Min Act: -0.0000

Data Index: 1642459 (Python Code)

Max Activating Token Index: 85

Text #17

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0746. Min Act: -0.0000

Data Index: 1465762 (Python Code)

Max Activating Token Index: 693

Text #18

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0762. Min Act: -0.0000

Data Index: 1627722 (Python Code)

Max Activating Token Index: 947

Text #19

Max Range: 0.1016. Min Range: -0.1016

Max Act: 0.0757. Min Act: -0.0000

Data Index: 1298542 (C4 (Web Text))

Max Activating Token Index: 169