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

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

Neuron 1000 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0976. Min Range: -0.0976

Max Act: 0.0976. Min Act: -0.0001

Data Index: 16231 (C4 (Web Text))

Max Activating Token Index: 547

Text #1

Max Range: 0.0976. Min Range: -0.0976

Max Act: 0.0798. Min Act: -0.0000

Data Index: 1174324 (C4 (Web Text))

Max Activating Token Index: 454

Text #2

Max Range: 0.0976. Min Range: -0.0976

Max Act: 0.0744. Min Act: -0.0000

Data Index: 710505 (C4 (Web Text))

Max Activating Token Index: 279

Text #3

Max Range: 0.0976. Min Range: -0.0976

Max Act: 0.0690. Min Act: -0.0000

Data Index: 619380 (C4 (Web Text))

Max Activating Token Index: 858

Text #4

Max Range: 0.0976. Min Range: -0.0976

Max Act: 0.0624. Min Act: -0.0000

Data Index: 938942 (C4 (Web Text))

Max Activating Token Index: 796

Text #5

Max Range: 0.0976. Min Range: -0.0976

Max Act: 0.0726. Min Act: -0.0000

Data Index: 1091443 (C4 (Web Text))

Max Activating Token Index: 623

Text #6

Max Range: 0.0976. Min Range: -0.0976

Max Act: 0.0635. Min Act: -0.0000

Data Index: 155580 (C4 (Web Text))

Max Activating Token Index: 799

Text #7

Max Range: 0.0976. Min Range: -0.0976

Max Act: 0.0643. Min Act: -0.0000

Data Index: 1000422 (C4 (Web Text))

Max Activating Token Index: 914

Text #8

Max Range: 0.0976. Min Range: -0.0976

Max Act: 0.0584. Min Act: -0.0001

Data Index: 616314 (C4 (Web Text))

Max Activating Token Index: 827

Text #9

Max Range: 0.0976. Min Range: -0.0976

Max Act: 0.0615. Min Act: -0.0000

Data Index: 800734 (C4 (Web Text))

Max Activating Token Index: 563

Text #10

Max Range: 0.0976. Min Range: -0.0976

Max Act: 0.0647. Min Act: -0.0000

Data Index: 1136310 (C4 (Web Text))

Max Activating Token Index: 792

Text #11

Max Range: 0.0976. Min Range: -0.0976

Max Act: 0.0599. Min Act: -0.0000

Data Index: 901920 (C4 (Web Text))

Max Activating Token Index: 388

Text #12

Max Range: 0.0976. Min Range: -0.0976

Max Act: 0.0567. Min Act: -0.0000

Data Index: 1563201 (Python Code)

Max Activating Token Index: 331

Text #13

Max Range: 0.0976. Min Range: -0.0976

Max Act: 0.0580. Min Act: -0.0000

Data Index: 36487 (C4 (Web Text))

Max Activating Token Index: 372

Text #14

Max Range: 0.0976. Min Range: -0.0976

Max Act: 0.0537. Min Act: -0.0000

Data Index: 1255807 (C4 (Web Text))

Max Activating Token Index: 799

Text #15

Max Range: 0.0976. Min Range: -0.0976

Max Act: 0.0600. Min Act: -0.0000

Data Index: 1241019 (C4 (Web Text))

Max Activating Token Index: 545

Text #16

Max Range: 0.0976. Min Range: -0.0976

Max Act: 0.0607. Min Act: -0.0000

Data Index: 1038258 (C4 (Web Text))

Max Activating Token Index: 906

Text #17

Max Range: 0.0976. Min Range: -0.0976

Max Act: 0.0637. Min Act: -0.0001

Data Index: 100466 (C4 (Web Text))

Max Activating Token Index: 746

Text #18

Max Range: 0.0976. Min Range: -0.0976

Max Act: 0.0591. Min Act: -0.0001

Data Index: 50141 (C4 (Web Text))

Max Activating Token Index: 772

Text #19

Max Range: 0.0976. Min Range: -0.0976

Max Act: 0.0535. Min Act: -0.0000

Data Index: 1350698 (C4 (Web Text))

Max Activating Token Index: 393