Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 390 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1906. Min Range: -0.1906

Max Act: 0.1906. Min Act: -0.0006

Data Index: 1046929 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.1906. Min Range: -0.1906

Max Act: 0.1873. Min Act: -0.0006

Data Index: 1023188 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 0.1906. Min Range: -0.1906

Max Act: 0.1864. Min Act: -0.0006

Data Index: 149025 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 0.1906. Min Range: -0.1906

Max Act: 0.1849. Min Act: -0.0006

Data Index: 378631 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 0.1906. Min Range: -0.1906

Max Act: 0.1770. Min Act: -0.0006

Data Index: 382962 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 0.1906. Min Range: -0.1906

Max Act: 0.1760. Min Act: -0.0006

Data Index: 447212 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 0.1906. Min Range: -0.1906

Max Act: 0.1745. Min Act: -0.0006

Data Index: 116194 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 0.1906. Min Range: -0.1906

Max Act: 0.1723. Min Act: -0.0006

Data Index: 725610 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 0.1906. Min Range: -0.1906

Max Act: 0.1652. Min Act: -0.0006

Data Index: 930911 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 0.1906. Min Range: -0.1906

Max Act: 0.1705. Min Act: -0.0006

Data Index: 370851 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 0.1906. Min Range: -0.1906

Max Act: 0.1694. Min Act: -0.0006

Data Index: 107852 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 0.1906. Min Range: -0.1906

Max Act: 0.1692. Min Act: -0.0006

Data Index: 1279975 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 0.1906. Min Range: -0.1906

Max Act: 0.1752. Min Act: -0.0006

Data Index: 1200777 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 0.1906. Min Range: -0.1906

Max Act: 0.1680. Min Act: -0.0006

Data Index: 828279 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 0.1906. Min Range: -0.1906

Max Act: 0.1673. Min Act: -0.0006

Data Index: 261367 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 0.1906. Min Range: -0.1906

Max Act: 0.1644. Min Act: -0.0006

Data Index: 1019358 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 0.1906. Min Range: -0.1906

Max Act: 0.1723. Min Act: -0.0006

Data Index: 97406 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 0.1906. Min Range: -0.1906

Max Act: 0.1755. Min Act: -0.0006

Data Index: 42308 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 0.1906. Min Range: -0.1906

Max Act: 0.1653. Min Act: -0.0006

Data Index: 690673 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 0.1906. Min Range: -0.1906

Max Act: 0.1654. Min Act: -0.0006

Data Index: 299112 (C4 (Web Text))

Max Activating Token Index: 1023