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

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

Neuron 2228 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1977. Min Range: -0.1977

Max Act: 0.1977. Min Act: -0.0001

Data Index: 1469009 (Python Code)

Max Activating Token Index: 409

Text #1

Max Range: 0.1977. Min Range: -0.1977

Max Act: 0.1721. Min Act: -0.0001

Data Index: 1650472 (Python Code)

Max Activating Token Index: 970

Text #2

Max Range: 0.1977. Min Range: -0.1977

Max Act: 0.1725. Min Act: -0.0001

Data Index: 1419364 (Python Code)

Max Activating Token Index: 79

Text #3

Max Range: 0.1977. Min Range: -0.1977

Max Act: 0.1668. Min Act: -0.0001

Data Index: 1423548 (Python Code)

Max Activating Token Index: 273

Text #4

Max Range: 0.1977. Min Range: -0.1977

Max Act: 0.1702. Min Act: -0.0001

Data Index: 1646205 (Python Code)

Max Activating Token Index: 149

Text #5

Max Range: 0.1977. Min Range: -0.1977

Max Act: 0.1580. Min Act: -0.0001

Data Index: 1538116 (Python Code)

Max Activating Token Index: 274

Text #6

Max Range: 0.1977. Min Range: -0.1977

Max Act: 0.1688. Min Act: -0.0001

Data Index: 1487479 (Python Code)

Max Activating Token Index: 760

Text #7

Max Range: 0.1977. Min Range: -0.1977

Max Act: 0.1637. Min Act: -0.0001

Data Index: 1548261 (Python Code)

Max Activating Token Index: 123

Text #8

Max Range: 0.1977. Min Range: -0.1977

Max Act: 0.1680. Min Act: -0.0001

Data Index: 1653868 (Python Code)

Max Activating Token Index: 443

Text #9

Max Range: 0.1977. Min Range: -0.1977

Max Act: 0.1673. Min Act: -0.0001

Data Index: 1457203 (Python Code)

Max Activating Token Index: 431

Text #10

Max Range: 0.1977. Min Range: -0.1977

Max Act: 0.1559. Min Act: -0.0001

Data Index: 1402075 (Python Code)

Max Activating Token Index: 836

Text #11

Max Range: 0.1977. Min Range: -0.1977

Max Act: 0.1675. Min Act: -0.0001

Data Index: 1607332 (Python Code)

Max Activating Token Index: 443

Text #12

Max Range: 0.1977. Min Range: -0.1977

Max Act: 0.1663. Min Act: -0.0001

Data Index: 1483771 (Python Code)

Max Activating Token Index: 315

Text #13

Max Range: 0.1977. Min Range: -0.1977

Max Act: 0.1608. Min Act: -0.0001

Data Index: 1492508 (Python Code)

Max Activating Token Index: 813

Text #14

Max Range: 0.1977. Min Range: -0.1977

Max Act: 0.1536. Min Act: -0.0001

Data Index: 1426405 (Python Code)

Max Activating Token Index: 901

Text #15

Max Range: 0.1977. Min Range: -0.1977

Max Act: 0.1654. Min Act: -0.0001

Data Index: 1381358 (Python Code)

Max Activating Token Index: 517

Text #16

Max Range: 0.1977. Min Range: -0.1977

Max Act: 0.1591. Min Act: -0.0001

Data Index: 1557999 (Python Code)

Max Activating Token Index: 244

Text #17

Max Range: 0.1977. Min Range: -0.1977

Max Act: 0.1654. Min Act: -0.0001

Data Index: 1431635 (Python Code)

Max Activating Token Index: 128

Text #18

Max Range: 0.1977. Min Range: -0.1977

Max Act: 0.1712. Min Act: -0.0001

Data Index: 1540388 (Python Code)

Max Activating Token Index: 725

Text #19

Max Range: 0.1977. Min Range: -0.1977

Max Act: 0.1585. Min Act: -0.0001

Data Index: 1389433 (Python Code)

Max Activating Token Index: 211