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

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

Neuron 3607 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: 0.0638. Min Range: -0.0638

Max Act: 0.0638. Min Act: -0.0003

Data Index: 951449 (C4 (Web Text))

Max Activating Token Index: 728

Text #1

Max Range: 0.0638. Min Range: -0.0638

Max Act: 0.0581. Min Act: -0.0003

Data Index: 532012 (C4 (Web Text))

Max Activating Token Index: 667

Text #2

Max Range: 0.0638. Min Range: -0.0638

Max Act: 0.0601. Min Act: -0.0003

Data Index: 373951 (C4 (Web Text))

Max Activating Token Index: 564

Text #3

Max Range: 0.0638. Min Range: -0.0638

Max Act: 0.0547. Min Act: -0.0003

Data Index: 1220757 (C4 (Web Text))

Max Activating Token Index: 936

Text #4

Max Range: 0.0638. Min Range: -0.0638

Max Act: 0.0520. Min Act: -0.0003

Data Index: 221782 (C4 (Web Text))

Max Activating Token Index: 244

Text #5

Max Range: 0.0638. Min Range: -0.0638

Max Act: 0.0517. Min Act: -0.0003

Data Index: 1123480 (C4 (Web Text))

Max Activating Token Index: 757

Text #6

Max Range: 0.0638. Min Range: -0.0638

Max Act: 0.0516. Min Act: -0.0003

Data Index: 40695 (C4 (Web Text))

Max Activating Token Index: 753

Text #7

Max Range: 0.0638. Min Range: -0.0638

Max Act: 0.0518. Min Act: -0.0003

Data Index: 908418 (C4 (Web Text))

Max Activating Token Index: 783

Text #8

Max Range: 0.0638. Min Range: -0.0638

Max Act: 0.0485. Min Act: -0.0003

Data Index: 925603 (C4 (Web Text))

Max Activating Token Index: 416

Text #9

Max Range: 0.0638. Min Range: -0.0638

Max Act: 0.0501. Min Act: -0.0003

Data Index: 1162395 (C4 (Web Text))

Max Activating Token Index: 889

Text #10

Max Range: 0.0638. Min Range: -0.0638

Max Act: 0.0473. Min Act: -0.0003

Data Index: 923771 (C4 (Web Text))

Max Activating Token Index: 523

Text #11

Max Range: 0.0638. Min Range: -0.0638

Max Act: 0.0481. Min Act: -0.0003

Data Index: 1095713 (C4 (Web Text))

Max Activating Token Index: 460

Text #12

Max Range: 0.0638. Min Range: -0.0638

Max Act: 0.0504. Min Act: -0.0003

Data Index: 593413 (C4 (Web Text))

Max Activating Token Index: 317

Text #13

Max Range: 0.0638. Min Range: -0.0638

Max Act: 0.0488. Min Act: -0.0003

Data Index: 1342650 (C4 (Web Text))

Max Activating Token Index: 929

Text #14

Max Range: 0.0638. Min Range: -0.0638

Max Act: 0.0486. Min Act: -0.0003

Data Index: 1348619 (C4 (Web Text))

Max Activating Token Index: 464

Text #15

Max Range: 0.0638. Min Range: -0.0638

Max Act: 0.0485. Min Act: -0.0003

Data Index: 1167513 (C4 (Web Text))

Max Activating Token Index: 573

Text #16

Max Range: 0.0638. Min Range: -0.0638

Max Act: 0.0475. Min Act: -0.0003

Data Index: 119902 (C4 (Web Text))

Max Activating Token Index: 800

Text #17

Max Range: 0.0638. Min Range: -0.0638

Max Act: 0.0470. Min Act: -0.0003

Data Index: 491515 (C4 (Web Text))

Max Activating Token Index: 13

Text #18

Max Range: 0.0638. Min Range: -0.0638

Max Act: 0.0451. Min Act: -0.0003

Data Index: 1049238 (C4 (Web Text))

Max Activating Token Index: 371

Text #19

Max Range: 0.0638. Min Range: -0.0638

Max Act: 0.0441. Min Act: -0.0003

Data Index: 655896 (C4 (Web Text))

Max Activating Token Index: 722