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

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

Neuron 360 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: 3.4785. Min Range: -3.4785

Max Act: 3.4785. Min Act: -0.0000

Data Index: 1449333 (Python Code)

Max Activating Token Index: 592

Text #1

Max Range: 3.4785. Min Range: -3.4785

Max Act: 3.2790. Min Act: -0.0000

Data Index: 55301 (C4 (Web Text))

Max Activating Token Index: 885

Text #2

Max Range: 3.4785. Min Range: -3.4785

Max Act: 3.2565. Min Act: -0.0000

Data Index: 1146252 (C4 (Web Text))

Max Activating Token Index: 710

Text #3

Max Range: 3.4785. Min Range: -3.4785

Max Act: 2.9438. Min Act: -0.0000

Data Index: 1346002 (C4 (Web Text))

Max Activating Token Index: 46

Text #4

Max Range: 3.4785. Min Range: -3.4785

Max Act: 2.6166. Min Act: -0.0000

Data Index: 989887 (C4 (Web Text))

Max Activating Token Index: 603

Text #5

Max Range: 3.4785. Min Range: -3.4785

Max Act: 2.5917. Min Act: -0.0000

Data Index: 143795 (C4 (Web Text))

Max Activating Token Index: 597

Text #6

Max Range: 3.4785. Min Range: -3.4785

Max Act: 2.7099. Min Act: -0.0000

Data Index: 1013122 (C4 (Web Text))

Max Activating Token Index: 223

Text #7

Max Range: 3.4785. Min Range: -3.4785

Max Act: 2.6069. Min Act: -0.0000

Data Index: 673496 (C4 (Web Text))

Max Activating Token Index: 984

Text #8

Max Range: 3.4785. Min Range: -3.4785

Max Act: 2.7161. Min Act: -0.0000

Data Index: 462874 (C4 (Web Text))

Max Activating Token Index: 673

Text #9

Max Range: 3.4785. Min Range: -3.4785

Max Act: 2.5997. Min Act: -0.0000

Data Index: 1137453 (C4 (Web Text))

Max Activating Token Index: 417

Text #10

Max Range: 3.4785. Min Range: -3.4785

Max Act: 2.5537. Min Act: -0.0000

Data Index: 1109410 (C4 (Web Text))

Max Activating Token Index: 961

Text #11

Max Range: 3.4785. Min Range: -3.4785

Max Act: 2.6676. Min Act: -0.0000

Data Index: 990673 (C4 (Web Text))

Max Activating Token Index: 666

Text #12

Max Range: 3.4785. Min Range: -3.4785

Max Act: 2.4083. Min Act: -0.0000

Data Index: 239387 (C4 (Web Text))

Max Activating Token Index: 516

Text #13

Max Range: 3.4785. Min Range: -3.4785

Max Act: 2.3804. Min Act: -0.0000

Data Index: 446706 (C4 (Web Text))

Max Activating Token Index: 697

Text #14

Max Range: 3.4785. Min Range: -3.4785

Max Act: 2.3590. Min Act: -0.0000

Data Index: 162628 (C4 (Web Text))

Max Activating Token Index: 364

Text #15

Max Range: 3.4785. Min Range: -3.4785

Max Act: 2.4264. Min Act: -0.0000

Data Index: 413662 (C4 (Web Text))

Max Activating Token Index: 139

Text #16

Max Range: 3.4785. Min Range: -3.4785

Max Act: 2.3906. Min Act: -0.0000

Data Index: 797911 (C4 (Web Text))

Max Activating Token Index: 624

Text #17

Max Range: 3.4785. Min Range: -3.4785

Max Act: 2.1267. Min Act: -0.0000

Data Index: 1346810 (C4 (Web Text))

Max Activating Token Index: 283

Text #18

Max Range: 3.4785. Min Range: -3.4785

Max Act: 2.4697. Min Act: -0.0000

Data Index: 259214 (C4 (Web Text))

Max Activating Token Index: 338

Text #19

Max Range: 3.4785. Min Range: -3.4785

Max Act: 2.4681. Min Act: -0.0000

Data Index: 831915 (C4 (Web Text))

Max Activating Token Index: 860