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

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

Neuron 4753 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: 0.0848. Min Range: -0.0848

Max Act: 0.0848. Min Act: -0.0002

Data Index: 78158 (C4 (Web Text))

Max Activating Token Index: 682

Text #1

Max Range: 0.0848. Min Range: -0.0848

Max Act: 0.0796. Min Act: -0.0002

Data Index: 1083934 (C4 (Web Text))

Max Activating Token Index: 93

Text #2

Max Range: 0.0848. Min Range: -0.0848

Max Act: 0.0768. Min Act: -0.0002

Data Index: 410640 (C4 (Web Text))

Max Activating Token Index: 437

Text #3

Max Range: 0.0848. Min Range: -0.0848

Max Act: 0.0739. Min Act: -0.0003

Data Index: 544463 (C4 (Web Text))

Max Activating Token Index: 463

Text #4

Max Range: 0.0848. Min Range: -0.0848

Max Act: 0.0702. Min Act: -0.0003

Data Index: 380295 (C4 (Web Text))

Max Activating Token Index: 731

Text #5

Max Range: 0.0848. Min Range: -0.0848

Max Act: 0.0725. Min Act: -0.0003

Data Index: 427437 (C4 (Web Text))

Max Activating Token Index: 453

Text #6

Max Range: 0.0848. Min Range: -0.0848

Max Act: 0.0676. Min Act: -0.0003

Data Index: 430813 (C4 (Web Text))

Max Activating Token Index: 182

Text #7

Max Range: 0.0848. Min Range: -0.0848

Max Act: 0.0652. Min Act: -0.0002

Data Index: 1153884 (C4 (Web Text))

Max Activating Token Index: 156

Text #8

Max Range: 0.0848. Min Range: -0.0848

Max Act: 0.0712. Min Act: -0.0003

Data Index: 836621 (C4 (Web Text))

Max Activating Token Index: 46

Text #9

Max Range: 0.0848. Min Range: -0.0848

Max Act: 0.0684. Min Act: -0.0002

Data Index: 153595 (C4 (Web Text))

Max Activating Token Index: 214

Text #10

Max Range: 0.0848. Min Range: -0.0848

Max Act: 0.0691. Min Act: -0.0002

Data Index: 6113 (C4 (Web Text))

Max Activating Token Index: 96

Text #11

Max Range: 0.0848. Min Range: -0.0848

Max Act: 0.0620. Min Act: -0.0002

Data Index: 1052457 (C4 (Web Text))

Max Activating Token Index: 350

Text #12

Max Range: 0.0848. Min Range: -0.0848

Max Act: 0.0680. Min Act: -0.0003

Data Index: 861511 (C4 (Web Text))

Max Activating Token Index: 297

Text #13

Max Range: 0.0848. Min Range: -0.0848

Max Act: 0.0659. Min Act: -0.0003

Data Index: 585859 (C4 (Web Text))

Max Activating Token Index: 309

Text #14

Max Range: 0.0848. Min Range: -0.0848

Max Act: 0.0634. Min Act: -0.0003

Data Index: 390549 (C4 (Web Text))

Max Activating Token Index: 329

Text #15

Max Range: 0.0848. Min Range: -0.0848

Max Act: 0.0632. Min Act: -0.0002

Data Index: 943765 (C4 (Web Text))

Max Activating Token Index: 203

Text #16

Max Range: 0.0848. Min Range: -0.0848

Max Act: 0.0639. Min Act: -0.0003

Data Index: 812660 (C4 (Web Text))

Max Activating Token Index: 922

Text #17

Max Range: 0.0848. Min Range: -0.0848

Max Act: 0.0633. Min Act: -0.0002

Data Index: 387328 (C4 (Web Text))

Max Activating Token Index: 115

Text #18

Max Range: 0.0848. Min Range: -0.0848

Max Act: 0.0606. Min Act: -0.0002

Data Index: 1083865 (C4 (Web Text))

Max Activating Token Index: 139

Text #19

Max Range: 0.0848. Min Range: -0.0848

Max Act: 0.0620. Min Act: -0.0003

Data Index: 570127 (C4 (Web Text))

Max Activating Token Index: 943