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

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

Neuron 570 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: 0.1843. Min Range: -0.1843

Max Act: 0.1843. Min Act: -0.0001

Data Index: 1473739 (Python Code)

Max Activating Token Index: 12

Text #1

Max Range: 0.1843. Min Range: -0.1843

Max Act: 0.1820. Min Act: -0.0001

Data Index: 1614542 (Python Code)

Max Activating Token Index: 24

Text #2

Max Range: 0.1843. Min Range: -0.1843

Max Act: 0.1697. Min Act: -0.0001

Data Index: 1497019 (Python Code)

Max Activating Token Index: 15

Text #3

Max Range: 0.1843. Min Range: -0.1843

Max Act: 0.1609. Min Act: -0.0001

Data Index: 1423199 (Python Code)

Max Activating Token Index: 13

Text #4

Max Range: 0.1843. Min Range: -0.1843

Max Act: 0.1654. Min Act: -0.0001

Data Index: 1623721 (Python Code)

Max Activating Token Index: 14

Text #5

Max Range: 0.1843. Min Range: -0.1843

Max Act: 0.1554. Min Act: -0.0001

Data Index: 1463195 (Python Code)

Max Activating Token Index: 615

Text #6

Max Range: 0.1843. Min Range: -0.1843

Max Act: 0.1599. Min Act: -0.0001

Data Index: 1479561 (Python Code)

Max Activating Token Index: 21

Text #7

Max Range: 0.1843. Min Range: -0.1843

Max Act: 0.1573. Min Act: -0.0001

Data Index: 1425184 (Python Code)

Max Activating Token Index: 17

Text #8

Max Range: 0.1843. Min Range: -0.1843

Max Act: 0.1491. Min Act: -0.0001

Data Index: 1646186 (Python Code)

Max Activating Token Index: 4

Text #9

Max Range: 0.1843. Min Range: -0.1843

Max Act: 0.1532. Min Act: -0.0001

Data Index: 1529252 (Python Code)

Max Activating Token Index: 15

Text #10

Max Range: 0.1843. Min Range: -0.1843

Max Act: 0.1536. Min Act: -0.0001

Data Index: 1381491 (Python Code)

Max Activating Token Index: 13

Text #11

Max Range: 0.1843. Min Range: -0.1843

Max Act: 0.1479. Min Act: -0.0001

Data Index: 1426024 (Python Code)

Max Activating Token Index: 18

Text #12

Max Range: 0.1843. Min Range: -0.1843

Max Act: 0.1444. Min Act: -0.0001

Data Index: 1641972 (Python Code)

Max Activating Token Index: 16

Text #13

Max Range: 0.1843. Min Range: -0.1843

Max Act: 0.1444. Min Act: -0.0001

Data Index: 1416125 (Python Code)

Max Activating Token Index: 42

Text #14

Max Range: 0.1843. Min Range: -0.1843

Max Act: 0.1488. Min Act: -0.0001

Data Index: 1468425 (Python Code)

Max Activating Token Index: 9

Text #15

Max Range: 0.1843. Min Range: -0.1843

Max Act: 0.1418. Min Act: -0.0001

Data Index: 1535866 (Python Code)

Max Activating Token Index: 13

Text #16

Max Range: 0.1843. Min Range: -0.1843

Max Act: 0.1449. Min Act: -0.0001

Data Index: 1603826 (Python Code)

Max Activating Token Index: 13

Text #17

Max Range: 0.1843. Min Range: -0.1843

Max Act: 0.1392. Min Act: -0.0001

Data Index: 1493824 (Python Code)

Max Activating Token Index: 21

Text #18

Max Range: 0.1843. Min Range: -0.1843

Max Act: 0.1445. Min Act: -0.0001

Data Index: 1464695 (Python Code)

Max Activating Token Index: 5

Text #19

Max Range: 0.1843. Min Range: -0.1843

Max Act: 0.1435. Min Act: -0.0001

Data Index: 1365850 (Python Code)

Max Activating Token Index: 10