Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3204 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.6890. Min Range: -1.6890

Max Act: 1.6890. Min Act: -0.0000

Data Index: 1637559 (Python Code)

Max Activating Token Index: 503

Text #1

Max Range: 1.6890. Min Range: -1.6890

Max Act: 1.6287. Min Act: -0.0000

Data Index: 1641193 (Python Code)

Max Activating Token Index: 602

Text #2

Max Range: 1.6890. Min Range: -1.6890

Max Act: 1.3978. Min Act: -0.0000

Data Index: 1395554 (Python Code)

Max Activating Token Index: 997

Text #3

Max Range: 1.6890. Min Range: -1.6890

Max Act: 1.4042. Min Act: -0.0000

Data Index: 1620851 (Python Code)

Max Activating Token Index: 955

Text #4

Max Range: 1.6890. Min Range: -1.6890

Max Act: 1.3389. Min Act: -0.0000

Data Index: 1438491 (Python Code)

Max Activating Token Index: 526

Text #5

Max Range: 1.6890. Min Range: -1.6890

Max Act: 1.3853. Min Act: -0.0000

Data Index: 1389281 (Python Code)

Max Activating Token Index: 165

Text #6

Max Range: 1.6890. Min Range: -1.6890

Max Act: 1.1478. Min Act: -0.0000

Data Index: 1371702 (Python Code)

Max Activating Token Index: 429

Text #7

Max Range: 1.6890. Min Range: -1.6890

Max Act: 1.1741. Min Act: -0.0000

Data Index: 1317471 (C4 (Web Text))

Max Activating Token Index: 651

Text #8

Max Range: 1.6890. Min Range: -1.6890

Max Act: 1.1689. Min Act: -0.0000

Data Index: 1568640 (Python Code)

Max Activating Token Index: 78

Text #9

Max Range: 1.6890. Min Range: -1.6890

Max Act: 1.1781. Min Act: -0.0000

Data Index: 1546146 (Python Code)

Max Activating Token Index: 477

Text #10

Max Range: 1.6890. Min Range: -1.6890

Max Act: 1.2117. Min Act: -0.0000

Data Index: 1488774 (Python Code)

Max Activating Token Index: 107

Text #11

Max Range: 1.6890. Min Range: -1.6890

Max Act: 1.1796. Min Act: -0.0000

Data Index: 1431269 (Python Code)

Max Activating Token Index: 158

Text #12

Max Range: 1.6890. Min Range: -1.6890

Max Act: 1.1440. Min Act: -0.0000

Data Index: 158462 (C4 (Web Text))

Max Activating Token Index: 759

Text #13

Max Range: 1.6890. Min Range: -1.6890

Max Act: 1.0741. Min Act: -0.0000

Data Index: 1472087 (Python Code)

Max Activating Token Index: 301

Text #14

Max Range: 1.6890. Min Range: -1.6890

Max Act: 1.1157. Min Act: -0.0000

Data Index: 1563832 (Python Code)

Max Activating Token Index: 475

Text #15

Max Range: 1.6890. Min Range: -1.6890

Max Act: 1.0843. Min Act: -0.0000

Data Index: 1365002 (Python Code)

Max Activating Token Index: 885

Text #16

Max Range: 1.6890. Min Range: -1.6890

Max Act: 1.1880. Min Act: -0.0000

Data Index: 656880 (C4 (Web Text))

Max Activating Token Index: 829

Text #17

Max Range: 1.6890. Min Range: -1.6890

Max Act: 0.9758. Min Act: -0.0000

Data Index: 837473 (C4 (Web Text))

Max Activating Token Index: 635

Text #18

Max Range: 1.6890. Min Range: -1.6890

Max Act: 1.1812. Min Act: -0.0000

Data Index: 1567635 (Python Code)

Max Activating Token Index: 163

Text #19

Max Range: 1.6890. Min Range: -1.6890

Max Act: 1.1886. Min Act: -0.0000

Data Index: 1573471 (Python Code)

Max Activating Token Index: 857