Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 323 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.9984. Min Range: -0.9984

Max Act: 0.9984. Min Act: -0.0001

Data Index: 416222 (C4 (Web Text))

Max Activating Token Index: 961

Text #1

Max Range: 0.9984. Min Range: -0.9984

Max Act: 0.9786. Min Act: -0.0000

Data Index: 430567 (C4 (Web Text))

Max Activating Token Index: 727

Text #2

Max Range: 0.9984. Min Range: -0.9984

Max Act: 0.8696. Min Act: -0.0001

Data Index: 85507 (C4 (Web Text))

Max Activating Token Index: 815

Text #3

Max Range: 0.9984. Min Range: -0.9984

Max Act: 0.7965. Min Act: -0.0000

Data Index: 209383 (C4 (Web Text))

Max Activating Token Index: 143

Text #4

Max Range: 0.9984. Min Range: -0.9984

Max Act: 0.8062. Min Act: -0.0001

Data Index: 610228 (C4 (Web Text))

Max Activating Token Index: 630

Text #5

Max Range: 0.9984. Min Range: -0.9984

Max Act: 0.7453. Min Act: -0.0000

Data Index: 439932 (C4 (Web Text))

Max Activating Token Index: 113

Text #6

Max Range: 0.9984. Min Range: -0.9984

Max Act: 0.7249. Min Act: -0.0001

Data Index: 637596 (C4 (Web Text))

Max Activating Token Index: 396

Text #7

Max Range: 0.9984. Min Range: -0.9984

Max Act: 0.7123. Min Act: -0.0000

Data Index: 730665 (C4 (Web Text))

Max Activating Token Index: 982

Text #8

Max Range: 0.9984. Min Range: -0.9984

Max Act: 0.7520. Min Act: -0.0000

Data Index: 849292 (C4 (Web Text))

Max Activating Token Index: 886

Text #9

Max Range: 0.9984. Min Range: -0.9984

Max Act: 0.7312. Min Act: -0.0000

Data Index: 1149632 (C4 (Web Text))

Max Activating Token Index: 160

Text #10

Max Range: 0.9984. Min Range: -0.9984

Max Act: 0.7128. Min Act: -0.0000

Data Index: 723812 (C4 (Web Text))

Max Activating Token Index: 704

Text #11

Max Range: 0.9984. Min Range: -0.9984

Max Act: 0.7043. Min Act: -0.0000

Data Index: 357463 (C4 (Web Text))

Max Activating Token Index: 851

Text #12

Max Range: 0.9984. Min Range: -0.9984

Max Act: 0.6989. Min Act: -0.0000

Data Index: 820930 (C4 (Web Text))

Max Activating Token Index: 320

Text #13

Max Range: 0.9984. Min Range: -0.9984

Max Act: 0.6736. Min Act: -0.0000

Data Index: 572443 (C4 (Web Text))

Max Activating Token Index: 387

Text #14

Max Range: 0.9984. Min Range: -0.9984

Max Act: 0.7040. Min Act: -0.0000

Data Index: 1150574 (C4 (Web Text))

Max Activating Token Index: 351

Text #15

Max Range: 0.9984. Min Range: -0.9984

Max Act: 0.7216. Min Act: -0.0000

Data Index: 880557 (C4 (Web Text))

Max Activating Token Index: 496

Text #16

Max Range: 0.9984. Min Range: -0.9984

Max Act: 0.6707. Min Act: -0.0000

Data Index: 775614 (C4 (Web Text))

Max Activating Token Index: 738

Text #17

Max Range: 0.9984. Min Range: -0.9984

Max Act: 0.6428. Min Act: -0.0000

Data Index: 763722 (C4 (Web Text))

Max Activating Token Index: 866

Text #18

Max Range: 0.9984. Min Range: -0.9984

Max Act: 0.6518. Min Act: -0.0000

Data Index: 1110915 (C4 (Web Text))

Max Activating Token Index: 817

Text #19

Max Range: 0.9984. Min Range: -0.9984

Max Act: 0.6511. Min Act: -0.0000

Data Index: 905659 (C4 (Web Text))

Max Activating Token Index: 766