Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3834 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0839. Min Range: -0.0839

Max Act: 0.0812. Min Act: -0.0000

Data Index: 495992 (C4 (Web Text))

Max Activating Token Index: 476

Text #1

Max Range: 0.0839. Min Range: -0.0839

Max Act: 0.0839. Min Act: -0.0000

Data Index: 1191921 (C4 (Web Text))

Max Activating Token Index: 556

Text #2

Max Range: 0.0839. Min Range: -0.0839

Max Act: 0.0771. Min Act: -0.0000

Data Index: 1494291 (Python Code)

Max Activating Token Index: 778

Text #3

Max Range: 0.0839. Min Range: -0.0839

Max Act: 0.0821. Min Act: -0.0000

Data Index: 451039 (C4 (Web Text))

Max Activating Token Index: 406

Text #4

Max Range: 0.0839. Min Range: -0.0839

Max Act: 0.0702. Min Act: -0.0000

Data Index: 1241260 (C4 (Web Text))

Max Activating Token Index: 716

Text #5

Max Range: 0.0839. Min Range: -0.0839

Max Act: 0.0708. Min Act: -0.0000

Data Index: 30352 (C4 (Web Text))

Max Activating Token Index: 873

Text #6

Max Range: 0.0839. Min Range: -0.0839

Max Act: 0.0631. Min Act: -0.0000

Data Index: 234765 (C4 (Web Text))

Max Activating Token Index: 578

Text #7

Max Range: 0.0839. Min Range: -0.0839

Max Act: 0.0643. Min Act: -0.0000

Data Index: 111488 (C4 (Web Text))

Max Activating Token Index: 949

Text #8

Max Range: 0.0839. Min Range: -0.0839

Max Act: 0.0686. Min Act: -0.0000

Data Index: 82448 (C4 (Web Text))

Max Activating Token Index: 411

Text #9

Max Range: 0.0839. Min Range: -0.0839

Max Act: 0.0611. Min Act: -0.0000

Data Index: 979629 (C4 (Web Text))

Max Activating Token Index: 849

Text #10

Max Range: 0.0839. Min Range: -0.0839

Max Act: 0.0660. Min Act: -0.0000

Data Index: 549267 (C4 (Web Text))

Max Activating Token Index: 854

Text #11

Max Range: 0.0839. Min Range: -0.0839

Max Act: 0.0659. Min Act: -0.0000

Data Index: 620473 (C4 (Web Text))

Max Activating Token Index: 763

Text #12

Max Range: 0.0839. Min Range: -0.0839

Max Act: 0.0585. Min Act: -0.0000

Data Index: 1199525 (C4 (Web Text))

Max Activating Token Index: 804

Text #13

Max Range: 0.0839. Min Range: -0.0839

Max Act: 0.0616. Min Act: -0.0001

Data Index: 1137121 (C4 (Web Text))

Max Activating Token Index: 858

Text #14

Max Range: 0.0839. Min Range: -0.0839

Max Act: 0.0615. Min Act: -0.0001

Data Index: 428054 (C4 (Web Text))

Max Activating Token Index: 194

Text #15

Max Range: 0.0839. Min Range: -0.0839

Max Act: 0.0637. Min Act: -0.0000

Data Index: 214601 (C4 (Web Text))

Max Activating Token Index: 755

Text #16

Max Range: 0.0839. Min Range: -0.0839

Max Act: 0.0613. Min Act: -0.0000

Data Index: 1114250 (C4 (Web Text))

Max Activating Token Index: 882

Text #17

Max Range: 0.0839. Min Range: -0.0839

Max Act: 0.0635. Min Act: -0.0001

Data Index: 26171 (C4 (Web Text))

Max Activating Token Index: 916

Text #18

Max Range: 0.0839. Min Range: -0.0839

Max Act: 0.0684. Min Act: -0.0001

Data Index: 127816 (C4 (Web Text))

Max Activating Token Index: 731

Text #19

Max Range: 0.0839. Min Range: -0.0839

Max Act: 0.0605. Min Act: -0.0000

Data Index: 262934 (C4 (Web Text))

Max Activating Token Index: 223