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

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

Neuron 2741 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: 0.6603. Min Range: -0.6603

Max Act: 0.6603. Min Act: -0.0000

Data Index: 207594 (C4 (Web Text))

Max Activating Token Index: 332

Text #1

Max Range: 0.6603. Min Range: -0.6603

Max Act: 0.6501. Min Act: -0.0000

Data Index: 913838 (C4 (Web Text))

Max Activating Token Index: 752

Text #2

Max Range: 0.6603. Min Range: -0.6603

Max Act: 0.5683. Min Act: -0.0000

Data Index: 129707 (C4 (Web Text))

Max Activating Token Index: 155

Text #3

Max Range: 0.6603. Min Range: -0.6603

Max Act: 0.6041. Min Act: -0.0000

Data Index: 840941 (C4 (Web Text))

Max Activating Token Index: 505

Text #4

Max Range: 0.6603. Min Range: -0.6603

Max Act: 0.5921. Min Act: -0.0000

Data Index: 1070838 (C4 (Web Text))

Max Activating Token Index: 687

Text #5

Max Range: 0.6603. Min Range: -0.6603

Max Act: 0.5753. Min Act: -0.0000

Data Index: 157469 (C4 (Web Text))

Max Activating Token Index: 500

Text #6

Max Range: 0.6603. Min Range: -0.6603

Max Act: 0.5814. Min Act: -0.0000

Data Index: 1264139 (C4 (Web Text))

Max Activating Token Index: 118

Text #7

Max Range: 0.6603. Min Range: -0.6603

Max Act: 0.5392. Min Act: -0.0000

Data Index: 676180 (C4 (Web Text))

Max Activating Token Index: 134

Text #8

Max Range: 0.6603. Min Range: -0.6603

Max Act: 0.5676. Min Act: -0.0000

Data Index: 620512 (C4 (Web Text))

Max Activating Token Index: 333

Text #9

Max Range: 0.6603. Min Range: -0.6603

Max Act: 0.5036. Min Act: -0.0000

Data Index: 913576 (C4 (Web Text))

Max Activating Token Index: 897

Text #10

Max Range: 0.6603. Min Range: -0.6603

Max Act: 0.4665. Min Act: -0.0000

Data Index: 14801 (C4 (Web Text))

Max Activating Token Index: 609

Text #11

Max Range: 0.6603. Min Range: -0.6603

Max Act: 0.5158. Min Act: -0.0000

Data Index: 635055 (C4 (Web Text))

Max Activating Token Index: 717

Text #12

Max Range: 0.6603. Min Range: -0.6603

Max Act: 0.5474. Min Act: -0.0000

Data Index: 1018696 (C4 (Web Text))

Max Activating Token Index: 80

Text #13

Max Range: 0.6603. Min Range: -0.6603

Max Act: 0.4786. Min Act: -0.0000

Data Index: 229362 (C4 (Web Text))

Max Activating Token Index: 131

Text #14

Max Range: 0.6603. Min Range: -0.6603

Max Act: 0.5030. Min Act: -0.0000

Data Index: 617410 (C4 (Web Text))

Max Activating Token Index: 111

Text #15

Max Range: 0.6603. Min Range: -0.6603

Max Act: 0.5065. Min Act: -0.0000

Data Index: 463362 (C4 (Web Text))

Max Activating Token Index: 40

Text #16

Max Range: 0.6603. Min Range: -0.6603

Max Act: 0.5013. Min Act: -0.0000

Data Index: 1108962 (C4 (Web Text))

Max Activating Token Index: 849

Text #17

Max Range: 0.6603. Min Range: -0.6603

Max Act: 0.4901. Min Act: -0.0000

Data Index: 348175 (C4 (Web Text))

Max Activating Token Index: 1013

Text #18

Max Range: 0.6603. Min Range: -0.6603

Max Act: 0.4743. Min Act: -0.0000

Data Index: 1060773 (C4 (Web Text))

Max Activating Token Index: 644

Text #19

Max Range: 0.6603. Min Range: -0.6603

Max Act: 0.4644. Min Act: -0.0000

Data Index: 1020791 (C4 (Web Text))

Max Activating Token Index: 986