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

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

Neuron 4552 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0913. Min Act: -0.0002

Data Index: 108095 (C4 (Web Text))

Max Activating Token Index: 511

Text #1

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0893. Min Act: -0.0002

Data Index: 167597 (C4 (Web Text))

Max Activating Token Index: 43

Text #2

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0809. Min Act: -0.0002

Data Index: 464929 (C4 (Web Text))

Max Activating Token Index: 255

Text #3

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0860. Min Act: -0.0002

Data Index: 700540 (C4 (Web Text))

Max Activating Token Index: 459

Text #4

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0768. Min Act: -0.0002

Data Index: 276117 (C4 (Web Text))

Max Activating Token Index: 9

Text #5

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0840. Min Act: -0.0002

Data Index: 1142319 (C4 (Web Text))

Max Activating Token Index: 113

Text #6

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0746. Min Act: -0.0002

Data Index: 314240 (C4 (Web Text))

Max Activating Token Index: 6

Text #7

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0832. Min Act: -0.0002

Data Index: 622067 (C4 (Web Text))

Max Activating Token Index: 4

Text #8

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0791. Min Act: -0.0002

Data Index: 714744 (C4 (Web Text))

Max Activating Token Index: 516

Text #9

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0727. Min Act: -0.0002

Data Index: 918052 (C4 (Web Text))

Max Activating Token Index: 350

Text #10

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0768. Min Act: -0.0002

Data Index: 466194 (C4 (Web Text))

Max Activating Token Index: 196

Text #11

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0748. Min Act: -0.0002

Data Index: 17899 (C4 (Web Text))

Max Activating Token Index: 634

Text #12

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0712. Min Act: -0.0002

Data Index: 15897 (C4 (Web Text))

Max Activating Token Index: 700

Text #13

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0696. Min Act: -0.0002

Data Index: 351321 (C4 (Web Text))

Max Activating Token Index: 3

Text #14

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0695. Min Act: -0.0002

Data Index: 376212 (C4 (Web Text))

Max Activating Token Index: 6

Text #15

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0716. Min Act: -0.0002

Data Index: 380468 (C4 (Web Text))

Max Activating Token Index: 426

Text #16

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0620. Min Act: -0.0002

Data Index: 392509 (C4 (Web Text))

Max Activating Token Index: 999

Text #17

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0603. Min Act: -0.0002

Data Index: 1325825 (C4 (Web Text))

Max Activating Token Index: 179

Text #18

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0741. Min Act: -0.0002

Data Index: 619108 (C4 (Web Text))

Max Activating Token Index: 219

Text #19

Max Range: 0.0913. Min Range: -0.0913

Max Act: 0.0652. Min Act: -0.0002

Data Index: 1080434 (C4 (Web Text))

Max Activating Token Index: 537