Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1135 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0908. Min Range: -0.0908

Max Act: 0.0908. Min Act: -0.0002

Data Index: 929743 (C4 (Web Text))

Max Activating Token Index: 281

Text #1

Max Range: 0.0908. Min Range: -0.0908

Max Act: 0.0870. Min Act: -0.0001

Data Index: 583046 (C4 (Web Text))

Max Activating Token Index: 57

Text #2

Max Range: 0.0908. Min Range: -0.0908

Max Act: 0.0864. Min Act: -0.0001

Data Index: 1612299 (Python Code)

Max Activating Token Index: 234

Text #3

Max Range: 0.0908. Min Range: -0.0908

Max Act: 0.0883. Min Act: -0.0001

Data Index: 912100 (C4 (Web Text))

Max Activating Token Index: 244

Text #4

Max Range: 0.0908. Min Range: -0.0908

Max Act: 0.0871. Min Act: -0.0001

Data Index: 1394163 (Python Code)

Max Activating Token Index: 158

Text #5

Max Range: 0.0908. Min Range: -0.0908

Max Act: 0.0839. Min Act: -0.0002

Data Index: 360927 (C4 (Web Text))

Max Activating Token Index: 222

Text #6

Max Range: 0.0908. Min Range: -0.0908

Max Act: 0.0836. Min Act: -0.0001

Data Index: 384976 (C4 (Web Text))

Max Activating Token Index: 146

Text #7

Max Range: 0.0908. Min Range: -0.0908

Max Act: 0.0847. Min Act: -0.0002

Data Index: 1171176 (C4 (Web Text))

Max Activating Token Index: 415

Text #8

Max Range: 0.0908. Min Range: -0.0908

Max Act: 0.0772. Min Act: -0.0001

Data Index: 112295 (C4 (Web Text))

Max Activating Token Index: 606

Text #9

Max Range: 0.0908. Min Range: -0.0908

Max Act: 0.0730. Min Act: -0.0001

Data Index: 1448462 (Python Code)

Max Activating Token Index: 498

Text #10

Max Range: 0.0908. Min Range: -0.0908

Max Act: 0.0781. Min Act: -0.0002

Data Index: 436566 (C4 (Web Text))

Max Activating Token Index: 58

Text #11

Max Range: 0.0908. Min Range: -0.0908

Max Act: 0.0775. Min Act: -0.0001

Data Index: 1482423 (Python Code)

Max Activating Token Index: 273

Text #12

Max Range: 0.0908. Min Range: -0.0908

Max Act: 0.0745. Min Act: -0.0002

Data Index: 462304 (C4 (Web Text))

Max Activating Token Index: 598

Text #13

Max Range: 0.0908. Min Range: -0.0908

Max Act: 0.0749. Min Act: -0.0001

Data Index: 258772 (C4 (Web Text))

Max Activating Token Index: 853

Text #14

Max Range: 0.0908. Min Range: -0.0908

Max Act: 0.0769. Min Act: -0.0001

Data Index: 1438778 (Python Code)

Max Activating Token Index: 214

Text #15

Max Range: 0.0908. Min Range: -0.0908

Max Act: 0.0713. Min Act: -0.0001

Data Index: 514448 (C4 (Web Text))

Max Activating Token Index: 477

Text #16

Max Range: 0.0908. Min Range: -0.0908

Max Act: 0.0781. Min Act: -0.0002

Data Index: 240133 (C4 (Web Text))

Max Activating Token Index: 936

Text #17

Max Range: 0.0908. Min Range: -0.0908

Max Act: 0.0759. Min Act: -0.0001

Data Index: 125423 (C4 (Web Text))

Max Activating Token Index: 5

Text #18

Max Range: 0.0908. Min Range: -0.0908

Max Act: 0.0673. Min Act: -0.0002

Data Index: 1234091 (C4 (Web Text))

Max Activating Token Index: 574

Text #19

Max Range: 0.0908. Min Range: -0.0908

Max Act: 0.0803. Min Act: -0.0002

Data Index: 599843 (C4 (Web Text))

Max Activating Token Index: 710