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

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

Neuron 524 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0843. Min Range: -0.0843

Max Act: 0.0837. Min Act: -0.0005

Data Index: 802843 (C4 (Web Text))

Max Activating Token Index: 983

Text #1

Max Range: 0.0843. Min Range: -0.0843

Max Act: 0.0843. Min Act: -0.0005

Data Index: 1102966 (C4 (Web Text))

Max Activating Token Index: 915

Text #2

Max Range: 0.0843. Min Range: -0.0843

Max Act: 0.0806. Min Act: -0.0005

Data Index: 306358 (C4 (Web Text))

Max Activating Token Index: 526

Text #3

Max Range: 0.0843. Min Range: -0.0843

Max Act: 0.0746. Min Act: -0.0005

Data Index: 198252 (C4 (Web Text))

Max Activating Token Index: 824

Text #4

Max Range: 0.0843. Min Range: -0.0843

Max Act: 0.0766. Min Act: -0.0005

Data Index: 323679 (C4 (Web Text))

Max Activating Token Index: 434

Text #5

Max Range: 0.0843. Min Range: -0.0843

Max Act: 0.0754. Min Act: -0.0005

Data Index: 1327582 (C4 (Web Text))

Max Activating Token Index: 209

Text #6

Max Range: 0.0843. Min Range: -0.0843

Max Act: 0.0712. Min Act: -0.0005

Data Index: 1108566 (C4 (Web Text))

Max Activating Token Index: 268

Text #7

Max Range: 0.0843. Min Range: -0.0843

Max Act: 0.0678. Min Act: -0.0005

Data Index: 1268863 (C4 (Web Text))

Max Activating Token Index: 301

Text #8

Max Range: 0.0843. Min Range: -0.0843

Max Act: 0.0707. Min Act: -0.0005

Data Index: 168686 (C4 (Web Text))

Max Activating Token Index: 401

Text #9

Max Range: 0.0843. Min Range: -0.0843

Max Act: 0.0653. Min Act: -0.0005

Data Index: 476635 (C4 (Web Text))

Max Activating Token Index: 137

Text #10

Max Range: 0.0843. Min Range: -0.0843

Max Act: 0.0715. Min Act: -0.0005

Data Index: 138862 (C4 (Web Text))

Max Activating Token Index: 577

Text #11

Max Range: 0.0843. Min Range: -0.0843

Max Act: 0.0742. Min Act: -0.0005

Data Index: 318714 (C4 (Web Text))

Max Activating Token Index: 340

Text #12

Max Range: 0.0843. Min Range: -0.0843

Max Act: 0.0739. Min Act: -0.0005

Data Index: 210559 (C4 (Web Text))

Max Activating Token Index: 107

Text #13

Max Range: 0.0843. Min Range: -0.0843

Max Act: 0.0650. Min Act: -0.0005

Data Index: 185176 (C4 (Web Text))

Max Activating Token Index: 769

Text #14

Max Range: 0.0843. Min Range: -0.0843

Max Act: 0.0633. Min Act: -0.0005

Data Index: 454562 (C4 (Web Text))

Max Activating Token Index: 595

Text #15

Max Range: 0.0843. Min Range: -0.0843

Max Act: 0.0634. Min Act: -0.0005

Data Index: 1046574 (C4 (Web Text))

Max Activating Token Index: 948

Text #16

Max Range: 0.0843. Min Range: -0.0843

Max Act: 0.0669. Min Act: -0.0005

Data Index: 75329 (C4 (Web Text))

Max Activating Token Index: 566

Text #17

Max Range: 0.0843. Min Range: -0.0843

Max Act: 0.0663. Min Act: -0.0005

Data Index: 862688 (C4 (Web Text))

Max Activating Token Index: 690

Text #18

Max Range: 0.0843. Min Range: -0.0843

Max Act: 0.0637. Min Act: -0.0005

Data Index: 406649 (C4 (Web Text))

Max Activating Token Index: 764

Text #19

Max Range: 0.0843. Min Range: -0.0843

Max Act: 0.0686. Min Act: -0.0005

Data Index: 507387 (C4 (Web Text))

Max Activating Token Index: 285