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

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

Neuron 4987 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2721. Min Range: -3.2721

Max Act: 3.1655. Min Act: -0.0000

Data Index: 1654607 (Python Code)

Max Activating Token Index: 517

Text #1

Max Range: 3.2721. Min Range: -3.2721

Max Act: 3.1570. Min Act: -0.0000

Data Index: 1526472 (Python Code)

Max Activating Token Index: 687

Text #2

Max Range: 3.2721. Min Range: -3.2721

Max Act: 3.2435. Min Act: -0.0000

Data Index: 1591189 (Python Code)

Max Activating Token Index: 545

Text #3

Max Range: 3.2721. Min Range: -3.2721

Max Act: 2.8121. Min Act: -0.0000

Data Index: 1647885 (Python Code)

Max Activating Token Index: 766

Text #4

Max Range: 3.2721. Min Range: -3.2721

Max Act: 3.2721. Min Act: -0.0000

Data Index: 1373447 (Python Code)

Max Activating Token Index: 732

Text #5

Max Range: 3.2721. Min Range: -3.2721

Max Act: 3.0611. Min Act: -0.0000

Data Index: 1569562 (Python Code)

Max Activating Token Index: 983

Text #6

Max Range: 3.2721. Min Range: -3.2721

Max Act: 3.2131. Min Act: -0.0000

Data Index: 1375984 (Python Code)

Max Activating Token Index: 531

Text #7

Max Range: 3.2721. Min Range: -3.2721

Max Act: 2.7575. Min Act: -0.0000

Data Index: 1523790 (Python Code)

Max Activating Token Index: 691

Text #8

Max Range: 3.2721. Min Range: -3.2721

Max Act: 3.0077. Min Act: -0.0000

Data Index: 1562551 (Python Code)

Max Activating Token Index: 533

Text #9

Max Range: 3.2721. Min Range: -3.2721

Max Act: 2.9814. Min Act: -0.0000

Data Index: 1564293 (Python Code)

Max Activating Token Index: 152

Text #10

Max Range: 3.2721. Min Range: -3.2721

Max Act: 2.8189. Min Act: -0.0000

Data Index: 1522018 (Python Code)

Max Activating Token Index: 774

Text #11

Max Range: 3.2721. Min Range: -3.2721

Max Act: 2.8191. Min Act: -0.0000

Data Index: 1482260 (Python Code)

Max Activating Token Index: 701

Text #12

Max Range: 3.2721. Min Range: -3.2721

Max Act: 2.9390. Min Act: -0.0000

Data Index: 1492300 (Python Code)

Max Activating Token Index: 898

Text #13

Max Range: 3.2721. Min Range: -3.2721

Max Act: 2.7259. Min Act: -0.0000

Data Index: 1396451 (Python Code)

Max Activating Token Index: 466

Text #14

Max Range: 3.2721. Min Range: -3.2721

Max Act: 2.5715. Min Act: -0.0000

Data Index: 1536329 (Python Code)

Max Activating Token Index: 79

Text #15

Max Range: 3.2721. Min Range: -3.2721

Max Act: 2.7273. Min Act: -0.0000

Data Index: 1431234 (Python Code)

Max Activating Token Index: 882

Text #16

Max Range: 3.2721. Min Range: -3.2721

Max Act: 2.7172. Min Act: -0.0000

Data Index: 1610921 (Python Code)

Max Activating Token Index: 528

Text #17

Max Range: 3.2721. Min Range: -3.2721

Max Act: 2.7841. Min Act: -0.0000

Data Index: 1391645 (Python Code)

Max Activating Token Index: 123

Text #18

Max Range: 3.2721. Min Range: -3.2721

Max Act: 2.7809. Min Act: -0.0000

Data Index: 1587552 (Python Code)

Max Activating Token Index: 793

Text #19

Max Range: 3.2721. Min Range: -3.2721

Max Act: 2.3808. Min Act: -0.0000

Data Index: 1452323 (Python Code)

Max Activating Token Index: 202