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

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

Neuron 657 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1117. Min Range: -0.1117

Max Act: 0.1117. Min Act: -0.0000

Data Index: 126488 (C4 (Web Text))

Max Activating Token Index: 518

Text #1

Max Range: 0.1117. Min Range: -0.1117

Max Act: 0.1010. Min Act: -0.0000

Data Index: 385393 (C4 (Web Text))

Max Activating Token Index: 60

Text #2

Max Range: 0.1117. Min Range: -0.1117

Max Act: 0.1037. Min Act: -0.0000

Data Index: 201017 (C4 (Web Text))

Max Activating Token Index: 209

Text #3

Max Range: 0.1117. Min Range: -0.1117

Max Act: 0.0839. Min Act: -0.0000

Data Index: 796328 (C4 (Web Text))

Max Activating Token Index: 537

Text #4

Max Range: 0.1117. Min Range: -0.1117

Max Act: 0.0757. Min Act: -0.0000

Data Index: 1424802 (Python Code)

Max Activating Token Index: 797

Text #5

Max Range: 0.1117. Min Range: -0.1117

Max Act: 0.0779. Min Act: -0.0000

Data Index: 48606 (C4 (Web Text))

Max Activating Token Index: 890

Text #6

Max Range: 0.1117. Min Range: -0.1117

Max Act: 0.0710. Min Act: -0.0000

Data Index: 1147399 (C4 (Web Text))

Max Activating Token Index: 954

Text #7

Max Range: 0.1117. Min Range: -0.1117

Max Act: 0.0723. Min Act: -0.0000

Data Index: 1203197 (C4 (Web Text))

Max Activating Token Index: 69

Text #8

Max Range: 0.1117. Min Range: -0.1117

Max Act: 0.0708. Min Act: -0.0000

Data Index: 1435035 (Python Code)

Max Activating Token Index: 779

Text #9

Max Range: 0.1117. Min Range: -0.1117

Max Act: 0.0710. Min Act: -0.0000

Data Index: 1356903 (C4 (Web Text))

Max Activating Token Index: 462

Text #10

Max Range: 0.1117. Min Range: -0.1117

Max Act: 0.0674. Min Act: -0.0000

Data Index: 418123 (C4 (Web Text))

Max Activating Token Index: 151

Text #11

Max Range: 0.1117. Min Range: -0.1117

Max Act: 0.0660. Min Act: -0.0000

Data Index: 1521493 (Python Code)

Max Activating Token Index: 521

Text #12

Max Range: 0.1117. Min Range: -0.1117

Max Act: 0.0689. Min Act: -0.0000

Data Index: 1333827 (C4 (Web Text))

Max Activating Token Index: 294

Text #13

Max Range: 0.1117. Min Range: -0.1117

Max Act: 0.0653. Min Act: -0.0000

Data Index: 853232 (C4 (Web Text))

Max Activating Token Index: 420

Text #14

Max Range: 0.1117. Min Range: -0.1117

Max Act: 0.0657. Min Act: -0.0000

Data Index: 1319961 (C4 (Web Text))

Max Activating Token Index: 619

Text #15

Max Range: 0.1117. Min Range: -0.1117

Max Act: 0.0673. Min Act: -0.0000

Data Index: 1276111 (C4 (Web Text))

Max Activating Token Index: 670

Text #16

Max Range: 0.1117. Min Range: -0.1117

Max Act: 0.0544. Min Act: -0.0000

Data Index: 1637015 (Python Code)

Max Activating Token Index: 815

Text #17

Max Range: 0.1117. Min Range: -0.1117

Max Act: 0.0659. Min Act: -0.0000

Data Index: 353740 (C4 (Web Text))

Max Activating Token Index: 195

Text #18

Max Range: 0.1117. Min Range: -0.1117

Max Act: 0.0604. Min Act: -0.0000

Data Index: 1518379 (Python Code)

Max Activating Token Index: 21

Text #19

Max Range: 0.1117. Min Range: -0.1117

Max Act: 0.0655. Min Act: -0.0000

Data Index: 741815 (C4 (Web Text))

Max Activating Token Index: 401