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

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

Neuron 1861 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0853. Min Range: -0.0853

Max Act: 0.0853. Min Act: -0.0001

Data Index: 733752 (C4 (Web Text))

Max Activating Token Index: 38

Text #1

Max Range: 0.0853. Min Range: -0.0853

Max Act: 0.0821. Min Act: -0.0001

Data Index: 588649 (C4 (Web Text))

Max Activating Token Index: 301

Text #2

Max Range: 0.0853. Min Range: -0.0853

Max Act: 0.0780. Min Act: -0.0001

Data Index: 172897 (C4 (Web Text))

Max Activating Token Index: 372

Text #3

Max Range: 0.0853. Min Range: -0.0853

Max Act: 0.0775. Min Act: -0.0001

Data Index: 830979 (C4 (Web Text))

Max Activating Token Index: 520

Text #4

Max Range: 0.0853. Min Range: -0.0853

Max Act: 0.0738. Min Act: -0.0001

Data Index: 608829 (C4 (Web Text))

Max Activating Token Index: 854

Text #5

Max Range: 0.0853. Min Range: -0.0853

Max Act: 0.0700. Min Act: -0.0001

Data Index: 690944 (C4 (Web Text))

Max Activating Token Index: 823

Text #6

Max Range: 0.0853. Min Range: -0.0853

Max Act: 0.0660. Min Act: -0.0001

Data Index: 300133 (C4 (Web Text))

Max Activating Token Index: 562

Text #7

Max Range: 0.0853. Min Range: -0.0853

Max Act: 0.0719. Min Act: -0.0001

Data Index: 810533 (C4 (Web Text))

Max Activating Token Index: 419

Text #8

Max Range: 0.0853. Min Range: -0.0853

Max Act: 0.0640. Min Act: -0.0001

Data Index: 882002 (C4 (Web Text))

Max Activating Token Index: 52

Text #9

Max Range: 0.0853. Min Range: -0.0853

Max Act: 0.0644. Min Act: -0.0001

Data Index: 522634 (C4 (Web Text))

Max Activating Token Index: 272

Text #10

Max Range: 0.0853. Min Range: -0.0853

Max Act: 0.0684. Min Act: -0.0001

Data Index: 369076 (C4 (Web Text))

Max Activating Token Index: 201

Text #11

Max Range: 0.0853. Min Range: -0.0853

Max Act: 0.0679. Min Act: -0.0001

Data Index: 830920 (C4 (Web Text))

Max Activating Token Index: 34

Text #12

Max Range: 0.0853. Min Range: -0.0853

Max Act: 0.0714. Min Act: -0.0001

Data Index: 311606 (C4 (Web Text))

Max Activating Token Index: 330

Text #13

Max Range: 0.0853. Min Range: -0.0853

Max Act: 0.0659. Min Act: -0.0001

Data Index: 1291803 (C4 (Web Text))

Max Activating Token Index: 411

Text #14

Max Range: 0.0853. Min Range: -0.0853

Max Act: 0.0682. Min Act: -0.0001

Data Index: 942576 (C4 (Web Text))

Max Activating Token Index: 935

Text #15

Max Range: 0.0853. Min Range: -0.0853

Max Act: 0.0705. Min Act: -0.0001

Data Index: 1567412 (Python Code)

Max Activating Token Index: 29

Text #16

Max Range: 0.0853. Min Range: -0.0853

Max Act: 0.0690. Min Act: -0.0001

Data Index: 1079835 (C4 (Web Text))

Max Activating Token Index: 648

Text #17

Max Range: 0.0853. Min Range: -0.0853

Max Act: 0.0700. Min Act: -0.0001

Data Index: 702483 (C4 (Web Text))

Max Activating Token Index: 853

Text #18

Max Range: 0.0853. Min Range: -0.0853

Max Act: 0.0676. Min Act: -0.0001

Data Index: 1321359 (C4 (Web Text))

Max Activating Token Index: 428

Text #19

Max Range: 0.0853. Min Range: -0.0853

Max Act: 0.0678. Min Act: -0.0001

Data Index: 1271126 (C4 (Web Text))

Max Activating Token Index: 663