Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4915 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 3.9063. Min Range: -3.9063

Max Act: 3.9063. Min Act: -0.0000

Data Index: 707592 (C4 (Web Text))

Max Activating Token Index: 916

Text #1

Max Range: 3.9063. Min Range: -3.9063

Max Act: 3.6919. Min Act: -0.0000

Data Index: 585562 (C4 (Web Text))

Max Activating Token Index: 973

Text #2

Max Range: 3.9063. Min Range: -3.9063

Max Act: 3.5719. Min Act: -0.0000

Data Index: 493796 (C4 (Web Text))

Max Activating Token Index: 20

Text #3

Max Range: 3.9063. Min Range: -3.9063

Max Act: 3.4708. Min Act: -0.0000

Data Index: 1489695 (Python Code)

Max Activating Token Index: 661

Text #4

Max Range: 3.9063. Min Range: -3.9063

Max Act: 3.3716. Min Act: -0.0000

Data Index: 172004 (C4 (Web Text))

Max Activating Token Index: 851

Text #5

Max Range: 3.9063. Min Range: -3.9063

Max Act: 3.1746. Min Act: -0.0000

Data Index: 1298137 (C4 (Web Text))

Max Activating Token Index: 889

Text #6

Max Range: 3.9063. Min Range: -3.9063

Max Act: 3.0316. Min Act: -0.0000

Data Index: 569280 (C4 (Web Text))

Max Activating Token Index: 504

Text #7

Max Range: 3.9063. Min Range: -3.9063

Max Act: 2.9910. Min Act: -0.0000

Data Index: 217401 (C4 (Web Text))

Max Activating Token Index: 502

Text #8

Max Range: 3.9063. Min Range: -3.9063

Max Act: 2.9431. Min Act: -0.0000

Data Index: 646059 (C4 (Web Text))

Max Activating Token Index: 921

Text #9

Max Range: 3.9063. Min Range: -3.9063

Max Act: 2.9231. Min Act: -0.0000

Data Index: 351398 (C4 (Web Text))

Max Activating Token Index: 687

Text #10

Max Range: 3.9063. Min Range: -3.9063

Max Act: 2.7684. Min Act: -0.0000

Data Index: 1030176 (C4 (Web Text))

Max Activating Token Index: 579

Text #11

Max Range: 3.9063. Min Range: -3.9063

Max Act: 3.1929. Min Act: -0.0000

Data Index: 792912 (C4 (Web Text))

Max Activating Token Index: 944

Text #12

Max Range: 3.9063. Min Range: -3.9063

Max Act: 2.8967. Min Act: -0.0000

Data Index: 836994 (C4 (Web Text))

Max Activating Token Index: 1000

Text #13

Max Range: 3.9063. Min Range: -3.9063

Max Act: 3.1837. Min Act: -0.0000

Data Index: 1050409 (C4 (Web Text))

Max Activating Token Index: 358

Text #14

Max Range: 3.9063. Min Range: -3.9063

Max Act: 3.1565. Min Act: -0.0000

Data Index: 150629 (C4 (Web Text))

Max Activating Token Index: 711

Text #15

Max Range: 3.9063. Min Range: -3.9063

Max Act: 3.0530. Min Act: -0.0000

Data Index: 318420 (C4 (Web Text))

Max Activating Token Index: 903

Text #16

Max Range: 3.9063. Min Range: -3.9063

Max Act: 3.0158. Min Act: -0.0000

Data Index: 641029 (C4 (Web Text))

Max Activating Token Index: 1018

Text #17

Max Range: 3.9063. Min Range: -3.9063

Max Act: 2.7303. Min Act: -0.0000

Data Index: 815713 (C4 (Web Text))

Max Activating Token Index: 444

Text #18

Max Range: 3.9063. Min Range: -3.9063

Max Act: 2.9894. Min Act: -0.0000

Data Index: 1291619 (C4 (Web Text))

Max Activating Token Index: 704

Text #19

Max Range: 3.9063. Min Range: -3.9063

Max Act: 2.9728. Min Act: -0.0000

Data Index: 1484801 (Python Code)

Max Activating Token Index: 704