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

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

Neuron 879 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1955. Min Range: -0.1955

Max Act: 0.1955. Min Act: -0.0000

Data Index: 1497799 (Python Code)

Max Activating Token Index: 443

Text #1

Max Range: 0.1955. Min Range: -0.1955

Max Act: 0.1955. Min Act: -0.0000

Data Index: 1501761 (Python Code)

Max Activating Token Index: 81

Text #2

Max Range: 0.1955. Min Range: -0.1955

Max Act: 0.1827. Min Act: -0.0000

Data Index: 1623876 (Python Code)

Max Activating Token Index: 54

Text #3

Max Range: 0.1955. Min Range: -0.1955

Max Act: 0.1873. Min Act: -0.0000

Data Index: 1515318 (Python Code)

Max Activating Token Index: 161

Text #4

Max Range: 0.1955. Min Range: -0.1955

Max Act: 0.1732. Min Act: -0.0000

Data Index: 1486766 (Python Code)

Max Activating Token Index: 671

Text #5

Max Range: 0.1955. Min Range: -0.1955

Max Act: 0.1878. Min Act: -0.0000

Data Index: 1629363 (Python Code)

Max Activating Token Index: 826

Text #6

Max Range: 0.1955. Min Range: -0.1955

Max Act: 0.1741. Min Act: -0.0000

Data Index: 1598223 (Python Code)

Max Activating Token Index: 596

Text #7

Max Range: 0.1955. Min Range: -0.1955

Max Act: 0.1601. Min Act: -0.0000

Data Index: 1467450 (Python Code)

Max Activating Token Index: 1006

Text #8

Max Range: 0.1955. Min Range: -0.1955

Max Act: 0.1504. Min Act: -0.0000

Data Index: 1439822 (Python Code)

Max Activating Token Index: 496

Text #9

Max Range: 0.1955. Min Range: -0.1955

Max Act: 0.1452. Min Act: -0.0000

Data Index: 1627775 (Python Code)

Max Activating Token Index: 1000

Text #10

Max Range: 0.1955. Min Range: -0.1955

Max Act: 0.1375. Min Act: -0.0000

Data Index: 1434722 (Python Code)

Max Activating Token Index: 697

Text #11

Max Range: 0.1955. Min Range: -0.1955

Max Act: 0.1577. Min Act: -0.0000

Data Index: 1490380 (Python Code)

Max Activating Token Index: 43

Text #12

Max Range: 0.1955. Min Range: -0.1955

Max Act: 0.1469. Min Act: -0.0000

Data Index: 1560592 (Python Code)

Max Activating Token Index: 146

Text #13

Max Range: 0.1955. Min Range: -0.1955

Max Act: 0.1443. Min Act: -0.0000

Data Index: 1432719 (Python Code)

Max Activating Token Index: 698

Text #14

Max Range: 0.1955. Min Range: -0.1955

Max Act: 0.1448. Min Act: -0.0000

Data Index: 1506849 (Python Code)

Max Activating Token Index: 127

Text #15

Max Range: 0.1955. Min Range: -0.1955

Max Act: 0.1552. Min Act: -0.0001

Data Index: 1588154 (Python Code)

Max Activating Token Index: 172

Text #16

Max Range: 0.1955. Min Range: -0.1955

Max Act: 0.1427. Min Act: -0.0000

Data Index: 1377833 (Python Code)

Max Activating Token Index: 32

Text #17

Max Range: 0.1955. Min Range: -0.1955

Max Act: 0.1383. Min Act: -0.0000

Data Index: 1457688 (Python Code)

Max Activating Token Index: 200

Text #18

Max Range: 0.1955. Min Range: -0.1955

Max Act: 0.1417. Min Act: -0.0000

Data Index: 1632443 (Python Code)

Max Activating Token Index: 80

Text #19

Max Range: 0.1955. Min Range: -0.1955

Max Act: 0.1498. Min Act: -0.0000

Data Index: 1565941 (Python Code)

Max Activating Token Index: 65