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

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

Neuron 1300 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0695. Min Range: -0.0695

Max Act: 0.0695. Min Act: -0.0002

Data Index: 1405583 (Python Code)

Max Activating Token Index: 90

Text #1

Max Range: 0.0695. Min Range: -0.0695

Max Act: 0.0690. Min Act: -0.0002

Data Index: 589759 (C4 (Web Text))

Max Activating Token Index: 505

Text #2

Max Range: 0.0695. Min Range: -0.0695

Max Act: 0.0684. Min Act: -0.0002

Data Index: 312528 (C4 (Web Text))

Max Activating Token Index: 248

Text #3

Max Range: 0.0695. Min Range: -0.0695

Max Act: 0.0683. Min Act: -0.0002

Data Index: 961685 (C4 (Web Text))

Max Activating Token Index: 9

Text #4

Max Range: 0.0695. Min Range: -0.0695

Max Act: 0.0676. Min Act: -0.0002

Data Index: 87537 (C4 (Web Text))

Max Activating Token Index: 215

Text #5

Max Range: 0.0695. Min Range: -0.0695

Max Act: 0.0678. Min Act: -0.0002

Data Index: 1537075 (Python Code)

Max Activating Token Index: 221

Text #6

Max Range: 0.0695. Min Range: -0.0695

Max Act: 0.0689. Min Act: -0.0002

Data Index: 518054 (C4 (Web Text))

Max Activating Token Index: 257

Text #7

Max Range: 0.0695. Min Range: -0.0695

Max Act: 0.0659. Min Act: -0.0002

Data Index: 1128160 (C4 (Web Text))

Max Activating Token Index: 4

Text #8

Max Range: 0.0695. Min Range: -0.0695

Max Act: 0.0670. Min Act: -0.0002

Data Index: 85597 (C4 (Web Text))

Max Activating Token Index: 3

Text #9

Max Range: 0.0695. Min Range: -0.0695

Max Act: 0.0668. Min Act: -0.0002

Data Index: 670202 (C4 (Web Text))

Max Activating Token Index: 573

Text #10

Max Range: 0.0695. Min Range: -0.0695

Max Act: 0.0682. Min Act: -0.0002

Data Index: 1127912 (C4 (Web Text))

Max Activating Token Index: 4

Text #11

Max Range: 0.0695. Min Range: -0.0695

Max Act: 0.0665. Min Act: -0.0002

Data Index: 1217765 (C4 (Web Text))

Max Activating Token Index: 226

Text #12

Max Range: 0.0695. Min Range: -0.0695

Max Act: 0.0664. Min Act: -0.0002

Data Index: 845788 (C4 (Web Text))

Max Activating Token Index: 279

Text #13

Max Range: 0.0695. Min Range: -0.0695

Max Act: 0.0676. Min Act: -0.0002

Data Index: 1126723 (C4 (Web Text))

Max Activating Token Index: 24

Text #14

Max Range: 0.0695. Min Range: -0.0695

Max Act: 0.0660. Min Act: -0.0002

Data Index: 1208387 (C4 (Web Text))

Max Activating Token Index: 291

Text #15

Max Range: 0.0695. Min Range: -0.0695

Max Act: 0.0660. Min Act: -0.0002

Data Index: 478538 (C4 (Web Text))

Max Activating Token Index: 3

Text #16

Max Range: 0.0695. Min Range: -0.0695

Max Act: 0.0660. Min Act: -0.0002

Data Index: 318570 (C4 (Web Text))

Max Activating Token Index: 714

Text #17

Max Range: 0.0695. Min Range: -0.0695

Max Act: 0.0657. Min Act: -0.0002

Data Index: 623396 (C4 (Web Text))

Max Activating Token Index: 203

Text #18

Max Range: 0.0695. Min Range: -0.0695

Max Act: 0.0657. Min Act: -0.0002

Data Index: 822360 (C4 (Web Text))

Max Activating Token Index: 427

Text #19

Max Range: 0.0695. Min Range: -0.0695

Max Act: 0.0657. Min Act: -0.0002

Data Index: 300738 (C4 (Web Text))

Max Activating Token Index: 69