Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3079 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1719. Min Range: -0.1719

Max Act: 0.1660. Min Act: -0.0003

Data Index: 1403958 (Python Code)

Max Activating Token Index: 218

Text #1

Max Range: 0.1719. Min Range: -0.1719

Max Act: 0.1719. Min Act: -0.0003

Data Index: 1373983 (Python Code)

Max Activating Token Index: 110

Text #2

Max Range: 0.1719. Min Range: -0.1719

Max Act: 0.1552. Min Act: -0.0003

Data Index: 1385054 (Python Code)

Max Activating Token Index: 382

Text #3

Max Range: 0.1719. Min Range: -0.1719

Max Act: 0.1473. Min Act: -0.0003

Data Index: 1631824 (Python Code)

Max Activating Token Index: 224

Text #4

Max Range: 0.1719. Min Range: -0.1719

Max Act: 0.1532. Min Act: -0.0002

Data Index: 1568031 (Python Code)

Max Activating Token Index: 320

Text #5

Max Range: 0.1719. Min Range: -0.1719

Max Act: 0.1557. Min Act: -0.0003

Data Index: 1513083 (Python Code)

Max Activating Token Index: 805

Text #6

Max Range: 0.1719. Min Range: -0.1719

Max Act: 0.1534. Min Act: -0.0003

Data Index: 1406834 (Python Code)

Max Activating Token Index: 98

Text #7

Max Range: 0.1719. Min Range: -0.1719

Max Act: 0.1622. Min Act: -0.0003

Data Index: 1456002 (Python Code)

Max Activating Token Index: 454

Text #8

Max Range: 0.1719. Min Range: -0.1719

Max Act: 0.1557. Min Act: -0.0003

Data Index: 1408409 (Python Code)

Max Activating Token Index: 308

Text #9

Max Range: 0.1719. Min Range: -0.1719

Max Act: 0.1540. Min Act: -0.0003

Data Index: 1427123 (Python Code)

Max Activating Token Index: 333

Text #10

Max Range: 0.1719. Min Range: -0.1719

Max Act: 0.1527. Min Act: -0.0003

Data Index: 1369407 (Python Code)

Max Activating Token Index: 478

Text #11

Max Range: 0.1719. Min Range: -0.1719

Max Act: 0.1549. Min Act: -0.0003

Data Index: 1521089 (Python Code)

Max Activating Token Index: 441

Text #12

Max Range: 0.1719. Min Range: -0.1719

Max Act: 0.1509. Min Act: -0.0003

Data Index: 1381160 (Python Code)

Max Activating Token Index: 780

Text #13

Max Range: 0.1719. Min Range: -0.1719

Max Act: 0.1516. Min Act: -0.0003

Data Index: 1367984 (Python Code)

Max Activating Token Index: 536

Text #14

Max Range: 0.1719. Min Range: -0.1719

Max Act: 0.1558. Min Act: -0.0003

Data Index: 1434851 (Python Code)

Max Activating Token Index: 414

Text #15

Max Range: 0.1719. Min Range: -0.1719

Max Act: 0.1498. Min Act: -0.0002

Data Index: 1477402 (Python Code)

Max Activating Token Index: 590

Text #16

Max Range: 0.1719. Min Range: -0.1719

Max Act: 0.1517. Min Act: -0.0003

Data Index: 1528642 (Python Code)

Max Activating Token Index: 604

Text #17

Max Range: 0.1719. Min Range: -0.1719

Max Act: 0.1488. Min Act: -0.0003

Data Index: 1546696 (Python Code)

Max Activating Token Index: 424

Text #18

Max Range: 0.1719. Min Range: -0.1719

Max Act: 0.1494. Min Act: -0.0002

Data Index: 1534817 (Python Code)

Max Activating Token Index: 675

Text #19

Max Range: 0.1719. Min Range: -0.1719

Max Act: 0.1544. Min Act: -0.0003

Data Index: 1550485 (Python Code)

Max Activating Token Index: 490