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

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

Neuron 4545 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8831. Min Range: -0.8831

Max Act: 0.8831. Min Act: -0.0002

Data Index: 1540761 (Python Code)

Max Activating Token Index: 303

Text #1

Max Range: 0.8831. Min Range: -0.8831

Max Act: 0.8417. Min Act: -0.0002

Data Index: 1550919 (Python Code)

Max Activating Token Index: 393

Text #2

Max Range: 0.8831. Min Range: -0.8831

Max Act: 0.8320. Min Act: -0.0002

Data Index: 1604703 (Python Code)

Max Activating Token Index: 607

Text #3

Max Range: 0.8831. Min Range: -0.8831

Max Act: 0.7738. Min Act: -0.0002

Data Index: 1511325 (Python Code)

Max Activating Token Index: 565

Text #4

Max Range: 0.8831. Min Range: -0.8831

Max Act: 0.7735. Min Act: -0.0002

Data Index: 1451341 (Python Code)

Max Activating Token Index: 216

Text #5

Max Range: 0.8831. Min Range: -0.8831

Max Act: 0.7747. Min Act: -0.0002

Data Index: 1494366 (Python Code)

Max Activating Token Index: 895

Text #6

Max Range: 0.8831. Min Range: -0.8831

Max Act: 0.8261. Min Act: -0.0002

Data Index: 1485201 (Python Code)

Max Activating Token Index: 143

Text #7

Max Range: 0.8831. Min Range: -0.8831

Max Act: 0.7256. Min Act: -0.0002

Data Index: 1365272 (Python Code)

Max Activating Token Index: 927

Text #8

Max Range: 0.8831. Min Range: -0.8831

Max Act: 0.7923. Min Act: -0.0002

Data Index: 1651399 (Python Code)

Max Activating Token Index: 606

Text #9

Max Range: 0.8831. Min Range: -0.8831

Max Act: 0.7978. Min Act: -0.0002

Data Index: 1401642 (Python Code)

Max Activating Token Index: 132

Text #10

Max Range: 0.8831. Min Range: -0.8831

Max Act: 0.7064. Min Act: -0.0002

Data Index: 1431922 (Python Code)

Max Activating Token Index: 776

Text #11

Max Range: 0.8831. Min Range: -0.8831

Max Act: 0.7733. Min Act: -0.0002

Data Index: 1423610 (Python Code)

Max Activating Token Index: 342

Text #12

Max Range: 0.8831. Min Range: -0.8831

Max Act: 0.7640. Min Act: -0.0002

Data Index: 1448824 (Python Code)

Max Activating Token Index: 162

Text #13

Max Range: 0.8831. Min Range: -0.8831

Max Act: 0.7461. Min Act: -0.0002

Data Index: 1472545 (Python Code)

Max Activating Token Index: 687

Text #14

Max Range: 0.8831. Min Range: -0.8831

Max Act: 0.7621. Min Act: -0.0002

Data Index: 1400482 (Python Code)

Max Activating Token Index: 6

Text #15

Max Range: 0.8831. Min Range: -0.8831

Max Act: 0.7655. Min Act: -0.0002

Data Index: 1373635 (Python Code)

Max Activating Token Index: 175

Text #16

Max Range: 0.8831. Min Range: -0.8831

Max Act: 0.6991. Min Act: -0.0002

Data Index: 1434505 (Python Code)

Max Activating Token Index: 762

Text #17

Max Range: 0.8831. Min Range: -0.8831

Max Act: 0.7045. Min Act: -0.0002

Data Index: 1570924 (Python Code)

Max Activating Token Index: 313

Text #18

Max Range: 0.8831. Min Range: -0.8831

Max Act: 0.8047. Min Act: -0.0002

Data Index: 1495940 (Python Code)

Max Activating Token Index: 585

Text #19

Max Range: 0.8831. Min Range: -0.8831

Max Act: 0.7169. Min Act: -0.0002

Data Index: 1405404 (Python Code)

Max Activating Token Index: 412