Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1269 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0882. Min Range: -0.0882

Max Act: 0.0882. Min Act: -0.0000

Data Index: 1253472 (C4 (Web Text))

Max Activating Token Index: 821

Text #1

Max Range: 0.0882. Min Range: -0.0882

Max Act: 0.0858. Min Act: -0.0000

Data Index: 1480675 (Python Code)

Max Activating Token Index: 138

Text #2

Max Range: 0.0882. Min Range: -0.0882

Max Act: 0.0844. Min Act: -0.0000

Data Index: 473444 (C4 (Web Text))

Max Activating Token Index: 906

Text #3

Max Range: 0.0882. Min Range: -0.0882

Max Act: 0.0720. Min Act: -0.0000

Data Index: 1238809 (C4 (Web Text))

Max Activating Token Index: 918

Text #4

Max Range: 0.0882. Min Range: -0.0882

Max Act: 0.0779. Min Act: -0.0000

Data Index: 1525001 (Python Code)

Max Activating Token Index: 695

Text #5

Max Range: 0.0882. Min Range: -0.0882

Max Act: 0.0675. Min Act: -0.0000

Data Index: 690823 (C4 (Web Text))

Max Activating Token Index: 838

Text #6

Max Range: 0.0882. Min Range: -0.0882

Max Act: 0.0730. Min Act: -0.0000

Data Index: 95154 (C4 (Web Text))

Max Activating Token Index: 400

Text #7

Max Range: 0.0882. Min Range: -0.0882

Max Act: 0.0785. Min Act: -0.0000

Data Index: 1439222 (Python Code)

Max Activating Token Index: 560

Text #8

Max Range: 0.0882. Min Range: -0.0882

Max Act: 0.0788. Min Act: -0.0000

Data Index: 1566435 (Python Code)

Max Activating Token Index: 286

Text #9

Max Range: 0.0882. Min Range: -0.0882

Max Act: 0.0749. Min Act: -0.0000

Data Index: 1375126 (Python Code)

Max Activating Token Index: 531

Text #10

Max Range: 0.0882. Min Range: -0.0882

Max Act: 0.0665. Min Act: -0.0000

Data Index: 156078 (C4 (Web Text))

Max Activating Token Index: 278

Text #11

Max Range: 0.0882. Min Range: -0.0882

Max Act: 0.0746. Min Act: -0.0000

Data Index: 1404729 (Python Code)

Max Activating Token Index: 628

Text #12

Max Range: 0.0882. Min Range: -0.0882

Max Act: 0.0730. Min Act: -0.0000

Data Index: 453127 (C4 (Web Text))

Max Activating Token Index: 313

Text #13

Max Range: 0.0882. Min Range: -0.0882

Max Act: 0.0655. Min Act: -0.0000

Data Index: 901845 (C4 (Web Text))

Max Activating Token Index: 142

Text #14

Max Range: 0.0882. Min Range: -0.0882

Max Act: 0.0635. Min Act: -0.0000

Data Index: 1648792 (Python Code)

Max Activating Token Index: 833

Text #15

Max Range: 0.0882. Min Range: -0.0882

Max Act: 0.0729. Min Act: -0.0000

Data Index: 512330 (C4 (Web Text))

Max Activating Token Index: 846

Text #16

Max Range: 0.0882. Min Range: -0.0882

Max Act: 0.0643. Min Act: -0.0000

Data Index: 125601 (C4 (Web Text))

Max Activating Token Index: 279

Text #17

Max Range: 0.0882. Min Range: -0.0882

Max Act: 0.0611. Min Act: -0.0000

Data Index: 1204963 (C4 (Web Text))

Max Activating Token Index: 806

Text #18

Max Range: 0.0882. Min Range: -0.0882

Max Act: 0.0670. Min Act: -0.0000

Data Index: 1570668 (Python Code)

Max Activating Token Index: 293

Text #19

Max Range: 0.0882. Min Range: -0.0882

Max Act: 0.0696. Min Act: -0.0000

Data Index: 422976 (C4 (Web Text))

Max Activating Token Index: 741