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

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

Neuron 579 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0779. Min Range: -0.0779

Max Act: 0.0779. Min Act: -0.0002

Data Index: 975102 (C4 (Web Text))

Max Activating Token Index: 221

Text #1

Max Range: 0.0779. Min Range: -0.0779

Max Act: 0.0670. Min Act: -0.0003

Data Index: 226958 (C4 (Web Text))

Max Activating Token Index: 957

Text #2

Max Range: 0.0779. Min Range: -0.0779

Max Act: 0.0653. Min Act: -0.0002

Data Index: 620070 (C4 (Web Text))

Max Activating Token Index: 494

Text #3

Max Range: 0.0779. Min Range: -0.0779

Max Act: 0.0639. Min Act: -0.0003

Data Index: 540715 (C4 (Web Text))

Max Activating Token Index: 877

Text #4

Max Range: 0.0779. Min Range: -0.0779

Max Act: 0.0620. Min Act: -0.0003

Data Index: 153620 (C4 (Web Text))

Max Activating Token Index: 914

Text #5

Max Range: 0.0779. Min Range: -0.0779

Max Act: 0.0582. Min Act: -0.0003

Data Index: 462357 (C4 (Web Text))

Max Activating Token Index: 995

Text #6

Max Range: 0.0779. Min Range: -0.0779

Max Act: 0.0548. Min Act: -0.0003

Data Index: 989138 (C4 (Web Text))

Max Activating Token Index: 693

Text #7

Max Range: 0.0779. Min Range: -0.0779

Max Act: 0.0562. Min Act: -0.0002

Data Index: 629519 (C4 (Web Text))

Max Activating Token Index: 592

Text #8

Max Range: 0.0779. Min Range: -0.0779

Max Act: 0.0593. Min Act: -0.0003

Data Index: 568479 (C4 (Web Text))

Max Activating Token Index: 298

Text #9

Max Range: 0.0779. Min Range: -0.0779

Max Act: 0.0536. Min Act: -0.0003

Data Index: 89946 (C4 (Web Text))

Max Activating Token Index: 762

Text #10

Max Range: 0.0779. Min Range: -0.0779

Max Act: 0.0535. Min Act: -0.0003

Data Index: 1246627 (C4 (Web Text))

Max Activating Token Index: 689

Text #11

Max Range: 0.0779. Min Range: -0.0779

Max Act: 0.0469. Min Act: -0.0003

Data Index: 873564 (C4 (Web Text))

Max Activating Token Index: 339

Text #12

Max Range: 0.0779. Min Range: -0.0779

Max Act: 0.0443. Min Act: -0.0003

Data Index: 606867 (C4 (Web Text))

Max Activating Token Index: 296

Text #13

Max Range: 0.0779. Min Range: -0.0779

Max Act: 0.0447. Min Act: -0.0002

Data Index: 24308 (C4 (Web Text))

Max Activating Token Index: 372

Text #14

Max Range: 0.0779. Min Range: -0.0779

Max Act: 0.0471. Min Act: -0.0002

Data Index: 637076 (C4 (Web Text))

Max Activating Token Index: 662

Text #15

Max Range: 0.0779. Min Range: -0.0779

Max Act: 0.0448. Min Act: -0.0003

Data Index: 872638 (C4 (Web Text))

Max Activating Token Index: 247

Text #16

Max Range: 0.0779. Min Range: -0.0779

Max Act: 0.0408. Min Act: -0.0002

Data Index: 855675 (C4 (Web Text))

Max Activating Token Index: 364

Text #17

Max Range: 0.0779. Min Range: -0.0779

Max Act: 0.0445. Min Act: -0.0002

Data Index: 969749 (C4 (Web Text))

Max Activating Token Index: 638

Text #18

Max Range: 0.0779. Min Range: -0.0779

Max Act: 0.0437. Min Act: -0.0002

Data Index: 1230092 (C4 (Web Text))

Max Activating Token Index: 814

Text #19

Max Range: 0.0779. Min Range: -0.0779

Max Act: 0.0402. Min Act: -0.0002

Data Index: 1071474 (C4 (Web Text))

Max Activating Token Index: 181