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

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

Neuron 3239 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0766. Min Act: -0.0002

Data Index: 1558162 (Python Code)

Max Activating Token Index: 122

Text #1

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0848. Min Act: -0.0002

Data Index: 100197 (C4 (Web Text))

Max Activating Token Index: 200

Text #2

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0867. Min Act: -0.0002

Data Index: 1603664 (Python Code)

Max Activating Token Index: 212

Text #3

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0756. Min Act: -0.0002

Data Index: 49957 (C4 (Web Text))

Max Activating Token Index: 993

Text #4

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0796. Min Act: -0.0002

Data Index: 1633128 (Python Code)

Max Activating Token Index: 239

Text #5

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0771. Min Act: -0.0002

Data Index: 450156 (C4 (Web Text))

Max Activating Token Index: 379

Text #6

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0692. Min Act: -0.0002

Data Index: 869044 (C4 (Web Text))

Max Activating Token Index: 223

Text #7

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0814. Min Act: -0.0002

Data Index: 1506021 (Python Code)

Max Activating Token Index: 569

Text #8

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0794. Min Act: -0.0002

Data Index: 1399326 (Python Code)

Max Activating Token Index: 101

Text #9

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0797. Min Act: -0.0002

Data Index: 995977 (C4 (Web Text))

Max Activating Token Index: 952

Text #10

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0726. Min Act: -0.0002

Data Index: 1490668 (Python Code)

Max Activating Token Index: 377

Text #11

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0770. Min Act: -0.0002

Data Index: 303854 (C4 (Web Text))

Max Activating Token Index: 205

Text #12

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0840. Min Act: -0.0002

Data Index: 1438012 (Python Code)

Max Activating Token Index: 134

Text #13

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0794. Min Act: -0.0002

Data Index: 242463 (C4 (Web Text))

Max Activating Token Index: 100

Text #14

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0713. Min Act: -0.0002

Data Index: 265798 (C4 (Web Text))

Max Activating Token Index: 76

Text #15

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0636. Min Act: -0.0002

Data Index: 858057 (C4 (Web Text))

Max Activating Token Index: 192

Text #16

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0687. Min Act: -0.0002

Data Index: 1499606 (Python Code)

Max Activating Token Index: 248

Text #17

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0585. Min Act: -0.0002

Data Index: 144227 (C4 (Web Text))

Max Activating Token Index: 226

Text #18

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0688. Min Act: -0.0002

Data Index: 1309 (C4 (Web Text))

Max Activating Token Index: 274

Text #19

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0684. Min Act: -0.0002

Data Index: 1502248 (Python Code)

Max Activating Token Index: 828