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

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

Neuron 1560 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1876. Min Range: -2.1876

Max Act: 2.1673. Min Act: -0.0000

Data Index: 1287466 (C4 (Web Text))

Max Activating Token Index: 164

Text #1

Max Range: 2.1876. Min Range: -2.1876

Max Act: 2.1326. Min Act: 0.0001

Data Index: 829303 (C4 (Web Text))

Max Activating Token Index: 983

Text #2

Max Range: 2.1876. Min Range: -2.1876

Max Act: 2.1876. Min Act: -0.0000

Data Index: 100946 (C4 (Web Text))

Max Activating Token Index: 754

Text #3

Max Range: 2.1876. Min Range: -2.1876

Max Act: 2.0937. Min Act: -0.0000

Data Index: 145537 (C4 (Web Text))

Max Activating Token Index: 584

Text #4

Max Range: 2.1876. Min Range: -2.1876

Max Act: 2.0501. Min Act: -0.0000

Data Index: 354496 (C4 (Web Text))

Max Activating Token Index: 859

Text #5

Max Range: 2.1876. Min Range: -2.1876

Max Act: 1.9631. Min Act: -0.0000

Data Index: 1187229 (C4 (Web Text))

Max Activating Token Index: 610

Text #6

Max Range: 2.1876. Min Range: -2.1876

Max Act: 1.9640. Min Act: -0.0000

Data Index: 502307 (C4 (Web Text))

Max Activating Token Index: 906

Text #7

Max Range: 2.1876. Min Range: -2.1876

Max Act: 2.0576. Min Act: 0.0000

Data Index: 1005116 (C4 (Web Text))

Max Activating Token Index: 237

Text #8

Max Range: 2.1876. Min Range: -2.1876

Max Act: 2.0309. Min Act: -0.0000

Data Index: 937704 (C4 (Web Text))

Max Activating Token Index: 389

Text #9

Max Range: 2.1876. Min Range: -2.1876

Max Act: 2.0119. Min Act: -0.0000

Data Index: 1098965 (C4 (Web Text))

Max Activating Token Index: 260

Text #10

Max Range: 2.1876. Min Range: -2.1876

Max Act: 1.8968. Min Act: 0.0000

Data Index: 569440 (C4 (Web Text))

Max Activating Token Index: 646

Text #11

Max Range: 2.1876. Min Range: -2.1876

Max Act: 1.8633. Min Act: -0.0000

Data Index: 583909 (C4 (Web Text))

Max Activating Token Index: 739

Text #12

Max Range: 2.1876. Min Range: -2.1876

Max Act: 1.8295. Min Act: -0.0000

Data Index: 1203493 (C4 (Web Text))

Max Activating Token Index: 551

Text #13

Max Range: 2.1876. Min Range: -2.1876

Max Act: 1.8488. Min Act: -0.0000

Data Index: 569768 (C4 (Web Text))

Max Activating Token Index: 218

Text #14

Max Range: 2.1876. Min Range: -2.1876

Max Act: 1.6973. Min Act: -0.0000

Data Index: 945137 (C4 (Web Text))

Max Activating Token Index: 863

Text #15

Max Range: 2.1876. Min Range: -2.1876

Max Act: 1.7954. Min Act: -0.0000

Data Index: 542718 (C4 (Web Text))

Max Activating Token Index: 944

Text #16

Max Range: 2.1876. Min Range: -2.1876

Max Act: 1.7896. Min Act: -0.0000

Data Index: 454965 (C4 (Web Text))

Max Activating Token Index: 674

Text #17

Max Range: 2.1876. Min Range: -2.1876

Max Act: 1.9360. Min Act: -0.0000

Data Index: 567738 (C4 (Web Text))

Max Activating Token Index: 594

Text #18

Max Range: 2.1876. Min Range: -2.1876

Max Act: 1.7811. Min Act: -0.0000

Data Index: 363822 (C4 (Web Text))

Max Activating Token Index: 566

Text #19

Max Range: 2.1876. Min Range: -2.1876

Max Act: 1.8718. Min Act: -0.0000

Data Index: 515114 (C4 (Web Text))

Max Activating Token Index: 676