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

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

Neuron 5844 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: 2.9836. Min Range: -2.9836

Max Act: 2.9836. Min Act: -0.0000

Data Index: 1433731 (Python Code)

Max Activating Token Index: 384

Text #1

Max Range: 2.9836. Min Range: -2.9836

Max Act: 2.6913. Min Act: -0.0000

Data Index: 1376735 (Python Code)

Max Activating Token Index: 581

Text #2

Max Range: 2.9836. Min Range: -2.9836

Max Act: 2.7717. Min Act: -0.0000

Data Index: 1502578 (Python Code)

Max Activating Token Index: 246

Text #3

Max Range: 2.9836. Min Range: -2.9836

Max Act: 2.3736. Min Act: -0.0000

Data Index: 1626376 (Python Code)

Max Activating Token Index: 723

Text #4

Max Range: 2.9836. Min Range: -2.9836

Max Act: 2.2975. Min Act: -0.0000

Data Index: 1650672 (Python Code)

Max Activating Token Index: 839

Text #5

Max Range: 2.9836. Min Range: -2.9836

Max Act: 1.8631. Min Act: -0.0000

Data Index: 490550 (C4 (Web Text))

Max Activating Token Index: 188

Text #6

Max Range: 2.9836. Min Range: -2.9836

Max Act: 2.2761. Min Act: -0.0000

Data Index: 1390985 (Python Code)

Max Activating Token Index: 482

Text #7

Max Range: 2.9836. Min Range: -2.9836

Max Act: 1.9620. Min Act: -0.0000

Data Index: 1450092 (Python Code)

Max Activating Token Index: 665

Text #8

Max Range: 2.9836. Min Range: -2.9836

Max Act: 1.7708. Min Act: -0.0000

Data Index: 1424120 (Python Code)

Max Activating Token Index: 316

Text #9

Max Range: 2.9836. Min Range: -2.9836

Max Act: 1.8557. Min Act: -0.0000

Data Index: 1625917 (Python Code)

Max Activating Token Index: 652

Text #10

Max Range: 2.9836. Min Range: -2.9836

Max Act: 1.7534. Min Act: -0.0000

Data Index: 1631548 (Python Code)

Max Activating Token Index: 609

Text #11

Max Range: 2.9836. Min Range: -2.9836

Max Act: 1.8344. Min Act: -0.0000

Data Index: 1651336 (Python Code)

Max Activating Token Index: 902

Text #12

Max Range: 2.9836. Min Range: -2.9836

Max Act: 1.8520. Min Act: -0.0000

Data Index: 1559505 (Python Code)

Max Activating Token Index: 521

Text #13

Max Range: 2.9836. Min Range: -2.9836

Max Act: 1.7466. Min Act: -0.0000

Data Index: 1620344 (Python Code)

Max Activating Token Index: 599

Text #14

Max Range: 2.9836. Min Range: -2.9836

Max Act: 1.7768. Min Act: -0.0000

Data Index: 1445478 (Python Code)

Max Activating Token Index: 539

Text #15

Max Range: 2.9836. Min Range: -2.9836

Max Act: 1.8721. Min Act: -0.0000

Data Index: 1561593 (Python Code)

Max Activating Token Index: 1005

Text #16

Max Range: 2.9836. Min Range: -2.9836

Max Act: 1.7773. Min Act: -0.0000

Data Index: 162308 (C4 (Web Text))

Max Activating Token Index: 142

Text #17

Max Range: 2.9836. Min Range: -2.9836

Max Act: 1.7680. Min Act: -0.0000

Data Index: 1562467 (Python Code)

Max Activating Token Index: 961

Text #18

Max Range: 2.9836. Min Range: -2.9836

Max Act: 1.4618. Min Act: -0.0000

Data Index: 1558775 (Python Code)

Max Activating Token Index: 691

Text #19

Max Range: 2.9836. Min Range: -2.9836

Max Act: 1.5108. Min Act: -0.0000

Data Index: 1522744 (Python Code)

Max Activating Token Index: 570