Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1002 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0908. Min Range: -0.0908

Max Act: 0.0897. Min Act: -0.0002

Data Index: 1547493 (Python Code)

Max Activating Token Index: 1023

Text #1

Max Range: 0.0908. Min Range: -0.0908

Max Act: 0.0908. Min Act: -0.0002

Data Index: 1451946 (Python Code)

Max Activating Token Index: 883

Text #2

Max Range: 0.0908. Min Range: -0.0908

Max Act: 0.0861. Min Act: -0.0002

Data Index: 1463106 (Python Code)

Max Activating Token Index: 1023

Text #3

Max Range: 0.0908. Min Range: -0.0908

Max Act: 0.0851. Min Act: -0.0002

Data Index: 1395651 (Python Code)

Max Activating Token Index: 370

Text #4

Max Range: 0.0908. Min Range: -0.0908

Max Act: 0.0883. Min Act: -0.0002

Data Index: 1520524 (Python Code)

Max Activating Token Index: 652

Text #5

Max Range: 0.0908. Min Range: -0.0908

Max Act: 0.0818. Min Act: -0.0002

Data Index: 1438085 (Python Code)

Max Activating Token Index: 915

Text #6

Max Range: 0.0908. Min Range: -0.0908

Max Act: 0.0846. Min Act: -0.0002

Data Index: 1581227 (Python Code)

Max Activating Token Index: 582

Text #7

Max Range: 0.0908. Min Range: -0.0908

Max Act: 0.0820. Min Act: -0.0002

Data Index: 1522410 (Python Code)

Max Activating Token Index: 616

Text #8

Max Range: 0.0908. Min Range: -0.0908

Max Act: 0.0820. Min Act: -0.0002

Data Index: 1445875 (Python Code)

Max Activating Token Index: 160

Text #9

Max Range: 0.0908. Min Range: -0.0908

Max Act: 0.0813. Min Act: -0.0002

Data Index: 1591403 (Python Code)

Max Activating Token Index: 916

Text #10

Max Range: 0.0908. Min Range: -0.0908

Max Act: 0.0779. Min Act: -0.0002

Data Index: 1379160 (Python Code)

Max Activating Token Index: 452

Text #11

Max Range: 0.0908. Min Range: -0.0908

Max Act: 0.0809. Min Act: -0.0002

Data Index: 1468911 (Python Code)

Max Activating Token Index: 542

Text #12

Max Range: 0.0908. Min Range: -0.0908

Max Act: 0.0808. Min Act: -0.0002

Data Index: 1590930 (Python Code)

Max Activating Token Index: 467

Text #13

Max Range: 0.0908. Min Range: -0.0908

Max Act: 0.0808. Min Act: -0.0002

Data Index: 1492903 (Python Code)

Max Activating Token Index: 874

Text #14

Max Range: 0.0908. Min Range: -0.0908

Max Act: 0.0775. Min Act: -0.0002

Data Index: 1561991 (Python Code)

Max Activating Token Index: 860

Text #15

Max Range: 0.0908. Min Range: -0.0908

Max Act: 0.0802. Min Act: -0.0002

Data Index: 1627447 (Python Code)

Max Activating Token Index: 784

Text #16

Max Range: 0.0908. Min Range: -0.0908

Max Act: 0.0802. Min Act: -0.0002

Data Index: 1521692 (Python Code)

Max Activating Token Index: 1023

Text #17

Max Range: 0.0908. Min Range: -0.0908

Max Act: 0.0802. Min Act: -0.0002

Data Index: 1563773 (Python Code)

Max Activating Token Index: 764

Text #18

Max Range: 0.0908. Min Range: -0.0908

Max Act: 0.0801. Min Act: -0.0002

Data Index: 1480631 (Python Code)

Max Activating Token Index: 185

Text #19

Max Range: 0.0908. Min Range: -0.0908

Max Act: 0.0801. Min Act: -0.0002

Data Index: 1374838 (Python Code)

Max Activating Token Index: 772