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

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

Neuron 4592 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1744. Min Range: -0.1744

Max Act: 0.1744. Min Act: -0.0000

Data Index: 447619 (C4 (Web Text))

Max Activating Token Index: 869

Text #1

Max Range: 0.1744. Min Range: -0.1744

Max Act: 0.1203. Min Act: -0.0000

Data Index: 1630283 (Python Code)

Max Activating Token Index: 933

Text #2

Max Range: 0.1744. Min Range: -0.1744

Max Act: 0.0956. Min Act: -0.0000

Data Index: 1535469 (Python Code)

Max Activating Token Index: 997

Text #3

Max Range: 0.1744. Min Range: -0.1744

Max Act: 0.1007. Min Act: -0.0000

Data Index: 543082 (C4 (Web Text))

Max Activating Token Index: 559

Text #4

Max Range: 0.1744. Min Range: -0.1744

Max Act: 0.0900. Min Act: -0.0000

Data Index: 934977 (C4 (Web Text))

Max Activating Token Index: 487

Text #5

Max Range: 0.1744. Min Range: -0.1744

Max Act: 0.0950. Min Act: -0.0000

Data Index: 630772 (C4 (Web Text))

Max Activating Token Index: 504

Text #6

Max Range: 0.1744. Min Range: -0.1744

Max Act: 0.0908. Min Act: -0.0000

Data Index: 275981 (C4 (Web Text))

Max Activating Token Index: 268

Text #7

Max Range: 0.1744. Min Range: -0.1744

Max Act: 0.0695. Min Act: -0.0000

Data Index: 812749 (C4 (Web Text))

Max Activating Token Index: 866

Text #8

Max Range: 0.1744. Min Range: -0.1744

Max Act: 0.0843. Min Act: -0.0000

Data Index: 1120511 (C4 (Web Text))

Max Activating Token Index: 541

Text #9

Max Range: 0.1744. Min Range: -0.1744

Max Act: 0.0824. Min Act: -0.0000

Data Index: 293992 (C4 (Web Text))

Max Activating Token Index: 682

Text #10

Max Range: 0.1744. Min Range: -0.1744

Max Act: 0.0832. Min Act: -0.0000

Data Index: 1355781 (C4 (Web Text))

Max Activating Token Index: 460

Text #11

Max Range: 0.1744. Min Range: -0.1744

Max Act: 0.0840. Min Act: -0.0000

Data Index: 4519 (C4 (Web Text))

Max Activating Token Index: 976

Text #12

Max Range: 0.1744. Min Range: -0.1744

Max Act: 0.0733. Min Act: -0.0000

Data Index: 365621 (C4 (Web Text))

Max Activating Token Index: 797

Text #13

Max Range: 0.1744. Min Range: -0.1744

Max Act: 0.0850. Min Act: -0.0000

Data Index: 610505 (C4 (Web Text))

Max Activating Token Index: 918

Text #14

Max Range: 0.1744. Min Range: -0.1744

Max Act: 0.0574. Min Act: -0.0000

Data Index: 828607 (C4 (Web Text))

Max Activating Token Index: 743

Text #15

Max Range: 0.1744. Min Range: -0.1744

Max Act: 0.0796. Min Act: -0.0000

Data Index: 1309227 (C4 (Web Text))

Max Activating Token Index: 465

Text #16

Max Range: 0.1744. Min Range: -0.1744

Max Act: 0.0805. Min Act: -0.0000

Data Index: 1136072 (C4 (Web Text))

Max Activating Token Index: 576

Text #17

Max Range: 0.1744. Min Range: -0.1744

Max Act: 0.0740. Min Act: -0.0000

Data Index: 268470 (C4 (Web Text))

Max Activating Token Index: 320

Text #18

Max Range: 0.1744. Min Range: -0.1744

Max Act: 0.0820. Min Act: -0.0000

Data Index: 710784 (C4 (Web Text))

Max Activating Token Index: 583

Text #19

Max Range: 0.1744. Min Range: -0.1744

Max Act: 0.0826. Min Act: -0.0000

Data Index: 1445384 (Python Code)

Max Activating Token Index: 409