Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1666 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.2815. Min Range: -0.2815

Max Act: 0.2815. Min Act: -0.0000

Data Index: 1535040 (Python Code)

Max Activating Token Index: 495

Text #1

Max Range: 0.2815. Min Range: -0.2815

Max Act: 0.2226. Min Act: -0.0000

Data Index: 603899 (C4 (Web Text))

Max Activating Token Index: 838

Text #2

Max Range: 0.2815. Min Range: -0.2815

Max Act: 0.2121. Min Act: -0.0000

Data Index: 1468424 (Python Code)

Max Activating Token Index: 748

Text #3

Max Range: 0.2815. Min Range: -0.2815

Max Act: 0.2337. Min Act: -0.0000

Data Index: 1112829 (C4 (Web Text))

Max Activating Token Index: 876

Text #4

Max Range: 0.2815. Min Range: -0.2815

Max Act: 0.2265. Min Act: -0.0000

Data Index: 1454203 (Python Code)

Max Activating Token Index: 138

Text #5

Max Range: 0.2815. Min Range: -0.2815

Max Act: 0.1814. Min Act: -0.0000

Data Index: 1587444 (Python Code)

Max Activating Token Index: 944

Text #6

Max Range: 0.2815. Min Range: -0.2815

Max Act: 0.1691. Min Act: -0.0000

Data Index: 1639980 (Python Code)

Max Activating Token Index: 981

Text #7

Max Range: 0.2815. Min Range: -0.2815

Max Act: 0.1834. Min Act: -0.0000

Data Index: 939534 (C4 (Web Text))

Max Activating Token Index: 558

Text #8

Max Range: 0.2815. Min Range: -0.2815

Max Act: 0.1758. Min Act: -0.0000

Data Index: 1274073 (C4 (Web Text))

Max Activating Token Index: 715

Text #9

Max Range: 0.2815. Min Range: -0.2815

Max Act: 0.1846. Min Act: -0.0000

Data Index: 1569269 (Python Code)

Max Activating Token Index: 798

Text #10

Max Range: 0.2815. Min Range: -0.2815

Max Act: 0.1923. Min Act: -0.0000

Data Index: 1498983 (Python Code)

Max Activating Token Index: 546

Text #11

Max Range: 0.2815. Min Range: -0.2815

Max Act: 0.1895. Min Act: -0.0000

Data Index: 1455713 (Python Code)

Max Activating Token Index: 749

Text #12

Max Range: 0.2815. Min Range: -0.2815

Max Act: 0.1891. Min Act: -0.0000

Data Index: 1612139 (Python Code)

Max Activating Token Index: 350

Text #13

Max Range: 0.2815. Min Range: -0.2815

Max Act: 0.1751. Min Act: -0.0000

Data Index: 1656138 (Python Code)

Max Activating Token Index: 947

Text #14

Max Range: 0.2815. Min Range: -0.2815

Max Act: 0.1903. Min Act: -0.0000

Data Index: 1618190 (Python Code)

Max Activating Token Index: 652

Text #15

Max Range: 0.2815. Min Range: -0.2815

Max Act: 0.1639. Min Act: -0.0000

Data Index: 1477610 (Python Code)

Max Activating Token Index: 839

Text #16

Max Range: 0.2815. Min Range: -0.2815

Max Act: 0.1706. Min Act: -0.0000

Data Index: 1606304 (Python Code)

Max Activating Token Index: 804

Text #17

Max Range: 0.2815. Min Range: -0.2815

Max Act: 0.1623. Min Act: -0.0000

Data Index: 1456889 (Python Code)

Max Activating Token Index: 170

Text #18

Max Range: 0.2815. Min Range: -0.2815

Max Act: 0.1642. Min Act: -0.0000

Data Index: 1398120 (Python Code)

Max Activating Token Index: 520

Text #19

Max Range: 0.2815. Min Range: -0.2815

Max Act: 0.1662. Min Act: -0.0000

Data Index: 1530612 (Python Code)

Max Activating Token Index: 715