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

Dataset: The Pile

Neuron 448 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3447. Min Range: -1.3447

Max Act: 1.3447. Min Act: -0.0000

Data Index: 404035 (The Pile)

Max Activating Token Index: 1003

Text #1

Max Range: 1.3447. Min Range: -1.3447

Max Act: 1.0719. Min Act: -0.0000

Data Index: 1850986 (The Pile)

Max Activating Token Index: 879

Text #2

Max Range: 1.3447. Min Range: -1.3447

Max Act: 1.0505. Min Act: -0.0000

Data Index: 1134620 (The Pile)

Max Activating Token Index: 83

Text #3

Max Range: 1.3447. Min Range: -1.3447

Max Act: 0.7894. Min Act: -0.0000

Data Index: 1379424 (The Pile)

Max Activating Token Index: 250

Text #4

Max Range: 1.3447. Min Range: -1.3447

Max Act: 0.8939. Min Act: -0.0000

Data Index: 1108114 (The Pile)

Max Activating Token Index: 587

Text #5

Max Range: 1.3447. Min Range: -1.3447

Max Act: 0.8837. Min Act: -0.0000

Data Index: 1030194 (The Pile)

Max Activating Token Index: 1018

Text #6

Max Range: 1.3447. Min Range: -1.3447

Max Act: 0.8959. Min Act: -0.0000

Data Index: 1945857 (The Pile)

Max Activating Token Index: 867

Text #7

Max Range: 1.3447. Min Range: -1.3447

Max Act: 0.8903. Min Act: -0.0000

Data Index: 1829895 (The Pile)

Max Activating Token Index: 997

Text #8

Max Range: 1.3447. Min Range: -1.3447

Max Act: 0.9012. Min Act: -0.0000

Data Index: 1703204 (The Pile)

Max Activating Token Index: 714

Text #9

Max Range: 1.3447. Min Range: -1.3447

Max Act: 0.8497. Min Act: -0.0000

Data Index: 1621856 (The Pile)

Max Activating Token Index: 455

Text #10

Max Range: 1.3447. Min Range: -1.3447

Max Act: 0.8015. Min Act: -0.0000

Data Index: 1107442 (The Pile)

Max Activating Token Index: 504

Text #11

Max Range: 1.3447. Min Range: -1.3447

Max Act: 0.7730. Min Act: -0.0000

Data Index: 763210 (The Pile)

Max Activating Token Index: 620

Text #12

Max Range: 1.3447. Min Range: -1.3447

Max Act: 0.8141. Min Act: -0.0000

Data Index: 1289762 (The Pile)

Max Activating Token Index: 646

Text #13

Max Range: 1.3447. Min Range: -1.3447

Max Act: 0.7555. Min Act: -0.0000

Data Index: 1633581 (The Pile)

Max Activating Token Index: 971

Text #14

Max Range: 1.3447. Min Range: -1.3447

Max Act: 0.7638. Min Act: -0.0000

Data Index: 258862 (The Pile)

Max Activating Token Index: 824

Text #15

Max Range: 1.3447. Min Range: -1.3447

Max Act: 0.7438. Min Act: -0.0000

Data Index: 1291988 (The Pile)

Max Activating Token Index: 28

Text #16

Max Range: 1.3447. Min Range: -1.3447

Max Act: 0.8000. Min Act: -0.0000

Data Index: 1072571 (The Pile)

Max Activating Token Index: 777

Text #17

Max Range: 1.3447. Min Range: -1.3447

Max Act: 0.7684. Min Act: -0.0000

Data Index: 1774646 (The Pile)

Max Activating Token Index: 352

Text #18

Max Range: 1.3447. Min Range: -1.3447

Max Act: 0.7555. Min Act: -0.0000

Data Index: 445990 (The Pile)

Max Activating Token Index: 914

Text #19

Max Range: 1.3447. Min Range: -1.3447

Max Act: 0.7257. Min Act: -0.0000

Data Index: 189694 (The Pile)

Max Activating Token Index: 641