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

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

Neuron 4957 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1394. Min Range: -1.1394

Max Act: 1.1394. Min Act: -0.0000

Data Index: 1384652 (Python Code)

Max Activating Token Index: 878

Text #1

Max Range: 1.1394. Min Range: -1.1394

Max Act: 0.9416. Min Act: -0.0000

Data Index: 1427447 (Python Code)

Max Activating Token Index: 1011

Text #2

Max Range: 1.1394. Min Range: -1.1394

Max Act: 0.8794. Min Act: -0.0000

Data Index: 1564136 (Python Code)

Max Activating Token Index: 421

Text #3

Max Range: 1.1394. Min Range: -1.1394

Max Act: 0.8624. Min Act: -0.0001

Data Index: 1533025 (Python Code)

Max Activating Token Index: 610

Text #4

Max Range: 1.1394. Min Range: -1.1394

Max Act: 0.8338. Min Act: -0.0000

Data Index: 1428979 (Python Code)

Max Activating Token Index: 811

Text #5

Max Range: 1.1394. Min Range: -1.1394

Max Act: 0.8655. Min Act: -0.0000

Data Index: 1543468 (Python Code)

Max Activating Token Index: 202

Text #6

Max Range: 1.1394. Min Range: -1.1394

Max Act: 0.8803. Min Act: -0.0000

Data Index: 1524085 (Python Code)

Max Activating Token Index: 561

Text #7

Max Range: 1.1394. Min Range: -1.1394

Max Act: 0.8120. Min Act: -0.0000

Data Index: 1533620 (Python Code)

Max Activating Token Index: 37

Text #8

Max Range: 1.1394. Min Range: -1.1394

Max Act: 0.8317. Min Act: -0.0001

Data Index: 1383742 (Python Code)

Max Activating Token Index: 506

Text #9

Max Range: 1.1394. Min Range: -1.1394

Max Act: 0.8886. Min Act: -0.0000

Data Index: 1476584 (Python Code)

Max Activating Token Index: 793

Text #10

Max Range: 1.1394. Min Range: -1.1394

Max Act: 0.7828. Min Act: -0.0001

Data Index: 1573712 (Python Code)

Max Activating Token Index: 675

Text #11

Max Range: 1.1394. Min Range: -1.1394

Max Act: 0.7146. Min Act: -0.0001

Data Index: 1419049 (Python Code)

Max Activating Token Index: 100

Text #12

Max Range: 1.1394. Min Range: -1.1394

Max Act: 0.7824. Min Act: -0.0000

Data Index: 1447062 (Python Code)

Max Activating Token Index: 781

Text #13

Max Range: 1.1394. Min Range: -1.1394

Max Act: 0.7253. Min Act: -0.0000

Data Index: 1604540 (Python Code)

Max Activating Token Index: 811

Text #14

Max Range: 1.1394. Min Range: -1.1394

Max Act: 0.7228. Min Act: -0.0000

Data Index: 1581076 (Python Code)

Max Activating Token Index: 433

Text #15

Max Range: 1.1394. Min Range: -1.1394

Max Act: 0.7021. Min Act: -0.0000

Data Index: 1489655 (Python Code)

Max Activating Token Index: 119

Text #16

Max Range: 1.1394. Min Range: -1.1394

Max Act: 0.6875. Min Act: -0.0000

Data Index: 1451673 (Python Code)

Max Activating Token Index: 761

Text #17

Max Range: 1.1394. Min Range: -1.1394

Max Act: 0.6710. Min Act: -0.0000

Data Index: 1480759 (Python Code)

Max Activating Token Index: 463

Text #18

Max Range: 1.1394. Min Range: -1.1394

Max Act: 0.6589. Min Act: -0.0000

Data Index: 1511275 (Python Code)

Max Activating Token Index: 695

Text #19

Max Range: 1.1394. Min Range: -1.1394

Max Act: 0.6843. Min Act: -0.0000

Data Index: 1500209 (Python Code)

Max Activating Token Index: 737