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

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

Neuron 5442 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3048. Min Range: -0.3048

Max Act: 0.3048. Min Act: -0.0000

Data Index: 1406280 (Python Code)

Max Activating Token Index: 408

Text #1

Max Range: 0.3048. Min Range: -0.3048

Max Act: 0.1875. Min Act: -0.0000

Data Index: 1426384 (Python Code)

Max Activating Token Index: 126

Text #2

Max Range: 0.3048. Min Range: -0.3048

Max Act: 0.1807. Min Act: -0.0001

Data Index: 1400768 (Python Code)

Max Activating Token Index: 562

Text #3

Max Range: 0.3048. Min Range: -0.3048

Max Act: 0.1864. Min Act: -0.0000

Data Index: 1610944 (Python Code)

Max Activating Token Index: 378

Text #4

Max Range: 0.3048. Min Range: -0.3048

Max Act: 0.1889. Min Act: -0.0001

Data Index: 1501053 (Python Code)

Max Activating Token Index: 55

Text #5

Max Range: 0.3048. Min Range: -0.3048

Max Act: 0.1947. Min Act: -0.0000

Data Index: 1472437 (Python Code)

Max Activating Token Index: 307

Text #6

Max Range: 0.3048. Min Range: -0.3048

Max Act: 0.1870. Min Act: -0.0001

Data Index: 1638538 (Python Code)

Max Activating Token Index: 508

Text #7

Max Range: 0.3048. Min Range: -0.3048

Max Act: 0.1769. Min Act: -0.0001

Data Index: 1501940 (Python Code)

Max Activating Token Index: 655

Text #8

Max Range: 0.3048. Min Range: -0.3048

Max Act: 0.1590. Min Act: -0.0001

Data Index: 1430516 (Python Code)

Max Activating Token Index: 419

Text #9

Max Range: 0.3048. Min Range: -0.3048

Max Act: 0.1758. Min Act: -0.0000

Data Index: 1508008 (Python Code)

Max Activating Token Index: 555

Text #10

Max Range: 0.3048. Min Range: -0.3048

Max Act: 0.1694. Min Act: -0.0000

Data Index: 1564914 (Python Code)

Max Activating Token Index: 422

Text #11

Max Range: 0.3048. Min Range: -0.3048

Max Act: 0.1570. Min Act: -0.0000

Data Index: 1470184 (Python Code)

Max Activating Token Index: 150

Text #12

Max Range: 0.3048. Min Range: -0.3048

Max Act: 0.1618. Min Act: -0.0000

Data Index: 1434548 (Python Code)

Max Activating Token Index: 271

Text #13

Max Range: 0.3048. Min Range: -0.3048

Max Act: 0.1737. Min Act: -0.0001

Data Index: 1382591 (Python Code)

Max Activating Token Index: 331

Text #14

Max Range: 0.3048. Min Range: -0.3048

Max Act: 0.1587. Min Act: -0.0000

Data Index: 1424126 (Python Code)

Max Activating Token Index: 152

Text #15

Max Range: 0.3048. Min Range: -0.3048

Max Act: 0.1389. Min Act: -0.0001

Data Index: 1386855 (Python Code)

Max Activating Token Index: 264

Text #16

Max Range: 0.3048. Min Range: -0.3048

Max Act: 0.1585. Min Act: -0.0001

Data Index: 1439123 (Python Code)

Max Activating Token Index: 187

Text #17

Max Range: 0.3048. Min Range: -0.3048

Max Act: 0.1689. Min Act: -0.0001

Data Index: 1573774 (Python Code)

Max Activating Token Index: 852

Text #18

Max Range: 0.3048. Min Range: -0.3048

Max Act: 0.1520. Min Act: -0.0000

Data Index: 1522147 (Python Code)

Max Activating Token Index: 150

Text #19

Max Range: 0.3048. Min Range: -0.3048

Max Act: 0.1468. Min Act: -0.0000

Data Index: 1482828 (Python Code)

Max Activating Token Index: 973