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

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

Neuron 1437 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0948. Min Range: -0.0948

Max Act: 0.0948. Min Act: -0.0000

Data Index: 1120043 (C4 (Web Text))

Max Activating Token Index: 164

Text #1

Max Range: 0.0948. Min Range: -0.0948

Max Act: 0.0915. Min Act: -0.0000

Data Index: 665300 (C4 (Web Text))

Max Activating Token Index: 674

Text #2

Max Range: 0.0948. Min Range: -0.0948

Max Act: 0.0931. Min Act: -0.0000

Data Index: 222717 (C4 (Web Text))

Max Activating Token Index: 577

Text #3

Max Range: 0.0948. Min Range: -0.0948

Max Act: 0.0908. Min Act: -0.0000

Data Index: 182555 (C4 (Web Text))

Max Activating Token Index: 22

Text #4

Max Range: 0.0948. Min Range: -0.0948

Max Act: 0.0858. Min Act: -0.0000

Data Index: 1017392 (C4 (Web Text))

Max Activating Token Index: 271

Text #5

Max Range: 0.0948. Min Range: -0.0948

Max Act: 0.0776. Min Act: 0.0000

Data Index: 470875 (C4 (Web Text))

Max Activating Token Index: 395

Text #6

Max Range: 0.0948. Min Range: -0.0948

Max Act: 0.0881. Min Act: -0.0000

Data Index: 1318565 (C4 (Web Text))

Max Activating Token Index: 674

Text #7

Max Range: 0.0948. Min Range: -0.0948

Max Act: 0.0825. Min Act: -0.0000

Data Index: 136715 (C4 (Web Text))

Max Activating Token Index: 239

Text #8

Max Range: 0.0948. Min Range: -0.0948

Max Act: 0.0778. Min Act: 0.0001

Data Index: 501578 (C4 (Web Text))

Max Activating Token Index: 87

Text #9

Max Range: 0.0948. Min Range: -0.0948

Max Act: 0.0762. Min Act: 0.0000

Data Index: 336060 (C4 (Web Text))

Max Activating Token Index: 745

Text #10

Max Range: 0.0948. Min Range: -0.0948

Max Act: 0.0720. Min Act: 0.0000

Data Index: 952539 (C4 (Web Text))

Max Activating Token Index: 309

Text #11

Max Range: 0.0948. Min Range: -0.0948

Max Act: 0.0760. Min Act: -0.0000

Data Index: 617878 (C4 (Web Text))

Max Activating Token Index: 309

Text #12

Max Range: 0.0948. Min Range: -0.0948

Max Act: 0.0719. Min Act: -0.0000

Data Index: 888350 (C4 (Web Text))

Max Activating Token Index: 470

Text #13

Max Range: 0.0948. Min Range: -0.0948

Max Act: 0.0690. Min Act: -0.0000

Data Index: 176934 (C4 (Web Text))

Max Activating Token Index: 650

Text #14

Max Range: 0.0948. Min Range: -0.0948

Max Act: 0.0718. Min Act: -0.0000

Data Index: 542395 (C4 (Web Text))

Max Activating Token Index: 108

Text #15

Max Range: 0.0948. Min Range: -0.0948

Max Act: 0.0716. Min Act: 0.0000

Data Index: 792493 (C4 (Web Text))

Max Activating Token Index: 229

Text #16

Max Range: 0.0948. Min Range: -0.0948

Max Act: 0.0689. Min Act: -0.0000

Data Index: 516795 (C4 (Web Text))

Max Activating Token Index: 356

Text #17

Max Range: 0.0948. Min Range: -0.0948

Max Act: 0.0671. Min Act: 0.0000

Data Index: 1192430 (C4 (Web Text))

Max Activating Token Index: 523

Text #18

Max Range: 0.0948. Min Range: -0.0948

Max Act: 0.0633. Min Act: 0.0000

Data Index: 964154 (C4 (Web Text))

Max Activating Token Index: 512

Text #19

Max Range: 0.0948. Min Range: -0.0948

Max Act: 0.0619. Min Act: -0.0000

Data Index: 633536 (C4 (Web Text))

Max Activating Token Index: 444