Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2404 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1665. Min Range: -0.1665

Max Act: 0.1653. Min Act: -0.0001

Data Index: 1399285 (Python Code)

Max Activating Token Index: 31

Text #1

Max Range: 0.1665. Min Range: -0.1665

Max Act: 0.1665. Min Act: -0.0001

Data Index: 1395190 (Python Code)

Max Activating Token Index: 48

Text #2

Max Range: 0.1665. Min Range: -0.1665

Max Act: 0.1659. Min Act: -0.0001

Data Index: 1582217 (Python Code)

Max Activating Token Index: 28

Text #3

Max Range: 0.1665. Min Range: -0.1665

Max Act: 0.1571. Min Act: -0.0001

Data Index: 1391907 (Python Code)

Max Activating Token Index: 23

Text #4

Max Range: 0.1665. Min Range: -0.1665

Max Act: 0.1650. Min Act: -0.0001

Data Index: 1641536 (Python Code)

Max Activating Token Index: 80

Text #5

Max Range: 0.1665. Min Range: -0.1665

Max Act: 0.1624. Min Act: -0.0001

Data Index: 1538115 (Python Code)

Max Activating Token Index: 49

Text #6

Max Range: 0.1665. Min Range: -0.1665

Max Act: 0.1548. Min Act: -0.0001

Data Index: 1384188 (Python Code)

Max Activating Token Index: 23

Text #7

Max Range: 0.1665. Min Range: -0.1665

Max Act: 0.1473. Min Act: -0.0001

Data Index: 1547576 (Python Code)

Max Activating Token Index: 23

Text #8

Max Range: 0.1665. Min Range: -0.1665

Max Act: 0.1526. Min Act: -0.0001

Data Index: 1515477 (Python Code)

Max Activating Token Index: 950

Text #9

Max Range: 0.1665. Min Range: -0.1665

Max Act: 0.1584. Min Act: -0.0001

Data Index: 1607498 (Python Code)

Max Activating Token Index: 686

Text #10

Max Range: 0.1665. Min Range: -0.1665

Max Act: 0.1575. Min Act: -0.0001

Data Index: 1562123 (Python Code)

Max Activating Token Index: 66

Text #11

Max Range: 0.1665. Min Range: -0.1665

Max Act: 0.1515. Min Act: -0.0001

Data Index: 1509718 (Python Code)

Max Activating Token Index: 780

Text #12

Max Range: 0.1665. Min Range: -0.1665

Max Act: 0.1460. Min Act: -0.0001

Data Index: 1478842 (Python Code)

Max Activating Token Index: 42

Text #13

Max Range: 0.1665. Min Range: -0.1665

Max Act: 0.1516. Min Act: -0.0001

Data Index: 1413038 (Python Code)

Max Activating Token Index: 12

Text #14

Max Range: 0.1665. Min Range: -0.1665

Max Act: 0.1517. Min Act: -0.0001

Data Index: 1513129 (Python Code)

Max Activating Token Index: 152

Text #15

Max Range: 0.1665. Min Range: -0.1665

Max Act: 0.1510. Min Act: -0.0001

Data Index: 1437644 (Python Code)

Max Activating Token Index: 995

Text #16

Max Range: 0.1665. Min Range: -0.1665

Max Act: 0.1557. Min Act: -0.0001

Data Index: 1449664 (Python Code)

Max Activating Token Index: 28

Text #17

Max Range: 0.1665. Min Range: -0.1665

Max Act: 0.1465. Min Act: -0.0001

Data Index: 1626956 (Python Code)

Max Activating Token Index: 34

Text #18

Max Range: 0.1665. Min Range: -0.1665

Max Act: 0.1512. Min Act: -0.0001

Data Index: 1361095 (Python Code)

Max Activating Token Index: 383

Text #19

Max Range: 0.1665. Min Range: -0.1665

Max Act: 0.1464. Min Act: -0.0001

Data Index: 1539337 (Python Code)

Max Activating Token Index: 48