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

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

Neuron 4118 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.8828. Min Range: -2.8828

Max Act: 2.8828. Min Act: -0.0000

Data Index: 1380690 (Python Code)

Max Activating Token Index: 543

Text #1

Max Range: 2.8828. Min Range: -2.8828

Max Act: 2.7588. Min Act: -0.0000

Data Index: 470817 (C4 (Web Text))

Max Activating Token Index: 872

Text #2

Max Range: 2.8828. Min Range: -2.8828

Max Act: 2.6121. Min Act: -0.0000

Data Index: 1512152 (Python Code)

Max Activating Token Index: 25

Text #3

Max Range: 2.8828. Min Range: -2.8828

Max Act: 2.4848. Min Act: -0.0000

Data Index: 1581989 (Python Code)

Max Activating Token Index: 771

Text #4

Max Range: 2.8828. Min Range: -2.8828

Max Act: 2.5826. Min Act: -0.0000

Data Index: 1546929 (Python Code)

Max Activating Token Index: 901

Text #5

Max Range: 2.8828. Min Range: -2.8828

Max Act: 2.5821. Min Act: -0.0000

Data Index: 1502475 (Python Code)

Max Activating Token Index: 1019

Text #6

Max Range: 2.8828. Min Range: -2.8828

Max Act: 2.4108. Min Act: -0.0000

Data Index: 913715 (C4 (Web Text))

Max Activating Token Index: 335

Text #7

Max Range: 2.8828. Min Range: -2.8828

Max Act: 2.3757. Min Act: -0.0000

Data Index: 1420558 (Python Code)

Max Activating Token Index: 917

Text #8

Max Range: 2.8828. Min Range: -2.8828

Max Act: 2.3575. Min Act: -0.0000

Data Index: 1383767 (Python Code)

Max Activating Token Index: 200

Text #9

Max Range: 2.8828. Min Range: -2.8828

Max Act: 2.1948. Min Act: -0.0000

Data Index: 1458800 (Python Code)

Max Activating Token Index: 652

Text #10

Max Range: 2.8828. Min Range: -2.8828

Max Act: 2.1504. Min Act: -0.0000

Data Index: 283008 (C4 (Web Text))

Max Activating Token Index: 466

Text #11

Max Range: 2.8828. Min Range: -2.8828

Max Act: 2.2691. Min Act: -0.0000

Data Index: 1591699 (Python Code)

Max Activating Token Index: 258

Text #12

Max Range: 2.8828. Min Range: -2.8828

Max Act: 2.1531. Min Act: -0.0000

Data Index: 1420450 (Python Code)

Max Activating Token Index: 933

Text #13

Max Range: 2.8828. Min Range: -2.8828

Max Act: 2.0555. Min Act: -0.0000

Data Index: 1065874 (C4 (Web Text))

Max Activating Token Index: 156

Text #14

Max Range: 2.8828. Min Range: -2.8828

Max Act: 2.1772. Min Act: -0.0000

Data Index: 1512053 (Python Code)

Max Activating Token Index: 922

Text #15

Max Range: 2.8828. Min Range: -2.8828

Max Act: 2.0734. Min Act: -0.0000

Data Index: 1379697 (Python Code)

Max Activating Token Index: 401

Text #16

Max Range: 2.8828. Min Range: -2.8828

Max Act: 2.1252. Min Act: -0.0000

Data Index: 1269342 (C4 (Web Text))

Max Activating Token Index: 928

Text #17

Max Range: 2.8828. Min Range: -2.8828

Max Act: 2.0053. Min Act: -0.0000

Data Index: 1639195 (Python Code)

Max Activating Token Index: 218

Text #18

Max Range: 2.8828. Min Range: -2.8828

Max Act: 2.2257. Min Act: -0.0000

Data Index: 1390384 (Python Code)

Max Activating Token Index: 584

Text #19

Max Range: 2.8828. Min Range: -2.8828

Max Act: 1.9744. Min Act: -0.0000

Data Index: 1487641 (Python Code)

Max Activating Token Index: 327