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

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

Neuron 5995 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1814. Min Range: -1.1814

Max Act: 1.1814. Min Act: -0.0000

Data Index: 1512548 (Python Code)

Max Activating Token Index: 190

Text #1

Max Range: 1.1814. Min Range: -1.1814

Max Act: 1.1582. Min Act: -0.0000

Data Index: 1630729 (Python Code)

Max Activating Token Index: 258

Text #2

Max Range: 1.1814. Min Range: -1.1814

Max Act: 1.1241. Min Act: -0.0000

Data Index: 1630893 (Python Code)

Max Activating Token Index: 105

Text #3

Max Range: 1.1814. Min Range: -1.1814

Max Act: 1.0695. Min Act: -0.0000

Data Index: 1395612 (Python Code)

Max Activating Token Index: 67

Text #4

Max Range: 1.1814. Min Range: -1.1814

Max Act: 1.0997. Min Act: -0.0000

Data Index: 1473437 (Python Code)

Max Activating Token Index: 70

Text #5

Max Range: 1.1814. Min Range: -1.1814

Max Act: 1.0679. Min Act: -0.0000

Data Index: 1589357 (Python Code)

Max Activating Token Index: 603

Text #6

Max Range: 1.1814. Min Range: -1.1814

Max Act: 1.0625. Min Act: -0.0000

Data Index: 1606348 (Python Code)

Max Activating Token Index: 650

Text #7

Max Range: 1.1814. Min Range: -1.1814

Max Act: 1.0603. Min Act: -0.0000

Data Index: 1421114 (Python Code)

Max Activating Token Index: 606

Text #8

Max Range: 1.1814. Min Range: -1.1814

Max Act: 1.0191. Min Act: -0.0000

Data Index: 1652973 (Python Code)

Max Activating Token Index: 772

Text #9

Max Range: 1.1814. Min Range: -1.1814

Max Act: 0.9635. Min Act: -0.0000

Data Index: 1438080 (Python Code)

Max Activating Token Index: 884

Text #10

Max Range: 1.1814. Min Range: -1.1814

Max Act: 1.0750. Min Act: -0.0000

Data Index: 1594447 (Python Code)

Max Activating Token Index: 296

Text #11

Max Range: 1.1814. Min Range: -1.1814

Max Act: 1.0251. Min Act: -0.0000

Data Index: 1618784 (Python Code)

Max Activating Token Index: 103

Text #12

Max Range: 1.1814. Min Range: -1.1814

Max Act: 1.0507. Min Act: -0.0000

Data Index: 1649689 (Python Code)

Max Activating Token Index: 374

Text #13

Max Range: 1.1814. Min Range: -1.1814

Max Act: 1.0015. Min Act: -0.0000

Data Index: 1390960 (Python Code)

Max Activating Token Index: 563

Text #14

Max Range: 1.1814. Min Range: -1.1814

Max Act: 1.0284. Min Act: -0.0000

Data Index: 1488313 (Python Code)

Max Activating Token Index: 360

Text #15

Max Range: 1.1814. Min Range: -1.1814

Max Act: 0.9949. Min Act: -0.0000

Data Index: 1530781 (Python Code)

Max Activating Token Index: 43

Text #16

Max Range: 1.1814. Min Range: -1.1814

Max Act: 0.9002. Min Act: -0.0000

Data Index: 1546600 (Python Code)

Max Activating Token Index: 871

Text #17

Max Range: 1.1814. Min Range: -1.1814

Max Act: 1.0447. Min Act: -0.0000

Data Index: 1384653 (Python Code)

Max Activating Token Index: 408

Text #18

Max Range: 1.1814. Min Range: -1.1814

Max Act: 0.9828. Min Act: -0.0000

Data Index: 1445957 (Python Code)

Max Activating Token Index: 478

Text #19

Max Range: 1.1814. Min Range: -1.1814

Max Act: 0.9522. Min Act: -0.0000

Data Index: 1624641 (Python Code)

Max Activating Token Index: 693