Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 147 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0848. Min Range: -0.0848

Max Act: 0.0848. Min Act: -0.0002

Data Index: 836741 (C4 (Web Text))

Max Activating Token Index: 705

Text #1

Max Range: 0.0848. Min Range: -0.0848

Max Act: 0.0743. Min Act: -0.0001

Data Index: 973822 (C4 (Web Text))

Max Activating Token Index: 998

Text #2

Max Range: 0.0848. Min Range: -0.0848

Max Act: 0.0730. Min Act: -0.0001

Data Index: 1177317 (C4 (Web Text))

Max Activating Token Index: 308

Text #3

Max Range: 0.0848. Min Range: -0.0848

Max Act: 0.0669. Min Act: -0.0002

Data Index: 73412 (C4 (Web Text))

Max Activating Token Index: 488

Text #4

Max Range: 0.0848. Min Range: -0.0848

Max Act: 0.0720. Min Act: -0.0002

Data Index: 1335014 (C4 (Web Text))

Max Activating Token Index: 477

Text #5

Max Range: 0.0848. Min Range: -0.0848

Max Act: 0.0642. Min Act: -0.0002

Data Index: 407361 (C4 (Web Text))

Max Activating Token Index: 499

Text #6

Max Range: 0.0848. Min Range: -0.0848

Max Act: 0.0694. Min Act: -0.0002

Data Index: 954132 (C4 (Web Text))

Max Activating Token Index: 626

Text #7

Max Range: 0.0848. Min Range: -0.0848

Max Act: 0.0694. Min Act: -0.0001

Data Index: 1182770 (C4 (Web Text))

Max Activating Token Index: 54

Text #8

Max Range: 0.0848. Min Range: -0.0848

Max Act: 0.0702. Min Act: -0.0002

Data Index: 653798 (C4 (Web Text))

Max Activating Token Index: 918

Text #9

Max Range: 0.0848. Min Range: -0.0848

Max Act: 0.0710. Min Act: -0.0002

Data Index: 1127547 (C4 (Web Text))

Max Activating Token Index: 912

Text #10

Max Range: 0.0848. Min Range: -0.0848

Max Act: 0.0659. Min Act: -0.0002

Data Index: 323448 (C4 (Web Text))

Max Activating Token Index: 145

Text #11

Max Range: 0.0848. Min Range: -0.0848

Max Act: 0.0680. Min Act: -0.0002

Data Index: 597531 (C4 (Web Text))

Max Activating Token Index: 793

Text #12

Max Range: 0.0848. Min Range: -0.0848

Max Act: 0.0656. Min Act: -0.0002

Data Index: 579837 (C4 (Web Text))

Max Activating Token Index: 564

Text #13

Max Range: 0.0848. Min Range: -0.0848

Max Act: 0.0657. Min Act: -0.0002

Data Index: 981175 (C4 (Web Text))

Max Activating Token Index: 452

Text #14

Max Range: 0.0848. Min Range: -0.0848

Max Act: 0.0615. Min Act: -0.0002

Data Index: 319363 (C4 (Web Text))

Max Activating Token Index: 470

Text #15

Max Range: 0.0848. Min Range: -0.0848

Max Act: 0.0666. Min Act: -0.0002

Data Index: 698978 (C4 (Web Text))

Max Activating Token Index: 359

Text #16

Max Range: 0.0848. Min Range: -0.0848

Max Act: 0.0644. Min Act: -0.0002

Data Index: 626736 (C4 (Web Text))

Max Activating Token Index: 459

Text #17

Max Range: 0.0848. Min Range: -0.0848

Max Act: 0.0627. Min Act: -0.0002

Data Index: 274690 (C4 (Web Text))

Max Activating Token Index: 662

Text #18

Max Range: 0.0848. Min Range: -0.0848

Max Act: 0.0672. Min Act: -0.0002

Data Index: 1358320 (C4 (Web Text))

Max Activating Token Index: 444

Text #19

Max Range: 0.0848. Min Range: -0.0848

Max Act: 0.0640. Min Act: -0.0001

Data Index: 1033334 (C4 (Web Text))

Max Activating Token Index: 482