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

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

Neuron 1119 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: 1.3835. Min Range: -1.3835

Max Act: 1.3835. Min Act: -0.0000

Data Index: 1519427 (Python Code)

Max Activating Token Index: 924

Text #1

Max Range: 1.3835. Min Range: -1.3835

Max Act: 1.1618. Min Act: -0.0000

Data Index: 1555124 (Python Code)

Max Activating Token Index: 190

Text #2

Max Range: 1.3835. Min Range: -1.3835

Max Act: 1.1015. Min Act: -0.0000

Data Index: 1444328 (Python Code)

Max Activating Token Index: 915

Text #3

Max Range: 1.3835. Min Range: -1.3835

Max Act: 1.0534. Min Act: -0.0000

Data Index: 1504337 (Python Code)

Max Activating Token Index: 542

Text #4

Max Range: 1.3835. Min Range: -1.3835

Max Act: 0.9686. Min Act: -0.0000

Data Index: 1548550 (Python Code)

Max Activating Token Index: 11

Text #5

Max Range: 1.3835. Min Range: -1.3835

Max Act: 0.9391. Min Act: -0.0000

Data Index: 1563369 (Python Code)

Max Activating Token Index: 432

Text #6

Max Range: 1.3835. Min Range: -1.3835

Max Act: 0.9800. Min Act: -0.0000

Data Index: 1594017 (Python Code)

Max Activating Token Index: 183

Text #7

Max Range: 1.3835. Min Range: -1.3835

Max Act: 0.8797. Min Act: -0.0000

Data Index: 955163 (C4 (Web Text))

Max Activating Token Index: 890

Text #8

Max Range: 1.3835. Min Range: -1.3835

Max Act: 0.8024. Min Act: -0.0000

Data Index: 1409039 (Python Code)

Max Activating Token Index: 160

Text #9

Max Range: 1.3835. Min Range: -1.3835

Max Act: 0.8356. Min Act: -0.0000

Data Index: 576545 (C4 (Web Text))

Max Activating Token Index: 197

Text #10

Max Range: 1.3835. Min Range: -1.3835

Max Act: 0.8365. Min Act: -0.0000

Data Index: 1431252 (Python Code)

Max Activating Token Index: 360

Text #11

Max Range: 1.3835. Min Range: -1.3835

Max Act: 0.9322. Min Act: -0.0000

Data Index: 1524464 (Python Code)

Max Activating Token Index: 759

Text #12

Max Range: 1.3835. Min Range: -1.3835

Max Act: 0.8258. Min Act: -0.0000

Data Index: 1466978 (Python Code)

Max Activating Token Index: 39

Text #13

Max Range: 1.3835. Min Range: -1.3835

Max Act: 0.8420. Min Act: -0.0000

Data Index: 1463874 (Python Code)

Max Activating Token Index: 62

Text #14

Max Range: 1.3835. Min Range: -1.3835

Max Act: 0.8074. Min Act: -0.0000

Data Index: 1300089 (C4 (Web Text))

Max Activating Token Index: 783

Text #15

Max Range: 1.3835. Min Range: -1.3835

Max Act: 0.8341. Min Act: -0.0000

Data Index: 1404919 (Python Code)

Max Activating Token Index: 737

Text #16

Max Range: 1.3835. Min Range: -1.3835

Max Act: 0.7914. Min Act: -0.0000

Data Index: 580966 (C4 (Web Text))

Max Activating Token Index: 421

Text #17

Max Range: 1.3835. Min Range: -1.3835

Max Act: 0.7546. Min Act: -0.0000

Data Index: 448870 (C4 (Web Text))

Max Activating Token Index: 698

Text #18

Max Range: 1.3835. Min Range: -1.3835

Max Act: 0.7442. Min Act: -0.0000

Data Index: 1481387 (Python Code)

Max Activating Token Index: 413

Text #19

Max Range: 1.3835. Min Range: -1.3835

Max Act: 0.8898. Min Act: -0.0000

Data Index: 1596300 (Python Code)

Max Activating Token Index: 972