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

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

Neuron 5020 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 9.1408. Min Range: -9.1408

Max Act: 9.1408. Min Act: -0.0000

Data Index: 1522893 (Python Code)

Max Activating Token Index: 689

Text #1

Max Range: 9.1408. Min Range: -9.1408

Max Act: 8.7445. Min Act: 0.0000

Data Index: 1481270 (Python Code)

Max Activating Token Index: 499

Text #2

Max Range: 9.1408. Min Range: -9.1408

Max Act: 8.8475. Min Act: -0.0000

Data Index: 1581484 (Python Code)

Max Activating Token Index: 576

Text #3

Max Range: 9.1408. Min Range: -9.1408

Max Act: 8.8391. Min Act: 0.0000

Data Index: 1559265 (Python Code)

Max Activating Token Index: 354

Text #4

Max Range: 9.1408. Min Range: -9.1408

Max Act: 8.3715. Min Act: -0.0000

Data Index: 1420864 (Python Code)

Max Activating Token Index: 708

Text #5

Max Range: 9.1408. Min Range: -9.1408

Max Act: 8.2071. Min Act: -0.0000

Data Index: 1643579 (Python Code)

Max Activating Token Index: 206

Text #6

Max Range: 9.1408. Min Range: -9.1408

Max Act: 7.9711. Min Act: -0.0000

Data Index: 1608828 (Python Code)

Max Activating Token Index: 687

Text #7

Max Range: 9.1408. Min Range: -9.1408

Max Act: 7.7366. Min Act: -0.0000

Data Index: 1405681 (Python Code)

Max Activating Token Index: 704

Text #8

Max Range: 9.1408. Min Range: -9.1408

Max Act: 7.9093. Min Act: -0.0000

Data Index: 1521386 (Python Code)

Max Activating Token Index: 629

Text #9

Max Range: 9.1408. Min Range: -9.1408

Max Act: 7.5014. Min Act: -0.0000

Data Index: 1627483 (Python Code)

Max Activating Token Index: 701

Text #10

Max Range: 9.1408. Min Range: -9.1408

Max Act: 7.6728. Min Act: -0.0000

Data Index: 1381576 (Python Code)

Max Activating Token Index: 826

Text #11

Max Range: 9.1408. Min Range: -9.1408

Max Act: 7.7377. Min Act: -0.0000

Data Index: 1504888 (Python Code)

Max Activating Token Index: 836

Text #12

Max Range: 9.1408. Min Range: -9.1408

Max Act: 7.5323. Min Act: -0.0000

Data Index: 1399257 (Python Code)

Max Activating Token Index: 616

Text #13

Max Range: 9.1408. Min Range: -9.1408

Max Act: 7.6686. Min Act: -0.0000

Data Index: 1542041 (Python Code)

Max Activating Token Index: 53

Text #14

Max Range: 9.1408. Min Range: -9.1408

Max Act: 7.4660. Min Act: -0.0000

Data Index: 1391766 (Python Code)

Max Activating Token Index: 143

Text #15

Max Range: 9.1408. Min Range: -9.1408

Max Act: 7.2502. Min Act: -0.0000

Data Index: 1568861 (Python Code)

Max Activating Token Index: 339

Text #16

Max Range: 9.1408. Min Range: -9.1408

Max Act: 6.9908. Min Act: -0.0000

Data Index: 1558908 (Python Code)

Max Activating Token Index: 142

Text #17

Max Range: 9.1408. Min Range: -9.1408

Max Act: 7.1429. Min Act: -0.0000

Data Index: 1475471 (Python Code)

Max Activating Token Index: 403

Text #18

Max Range: 9.1408. Min Range: -9.1408

Max Act: 7.0094. Min Act: -0.0000

Data Index: 1395252 (Python Code)

Max Activating Token Index: 882

Text #19

Max Range: 9.1408. Min Range: -9.1408

Max Act: 6.9810. Min Act: -0.0000

Data Index: 1568538 (Python Code)

Max Activating Token Index: 866