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

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

Neuron 5074 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.7713. Min Range: -4.7713

Max Act: 4.7029. Min Act: -0.0000

Data Index: 1374598 (Python Code)

Max Activating Token Index: 754

Text #1

Max Range: 4.7713. Min Range: -4.7713

Max Act: 4.7713. Min Act: -0.0000

Data Index: 1547099 (Python Code)

Max Activating Token Index: 985

Text #2

Max Range: 4.7713. Min Range: -4.7713

Max Act: 4.2501. Min Act: -0.0000

Data Index: 1442128 (Python Code)

Max Activating Token Index: 814

Text #3

Max Range: 4.7713. Min Range: -4.7713

Max Act: 4.1692. Min Act: -0.0000

Data Index: 1561742 (Python Code)

Max Activating Token Index: 892

Text #4

Max Range: 4.7713. Min Range: -4.7713

Max Act: 4.1423. Min Act: -0.0000

Data Index: 1447854 (Python Code)

Max Activating Token Index: 832

Text #5

Max Range: 4.7713. Min Range: -4.7713

Max Act: 3.8754. Min Act: -0.0000

Data Index: 1569294 (Python Code)

Max Activating Token Index: 692

Text #6

Max Range: 4.7713. Min Range: -4.7713

Max Act: 3.7202. Min Act: -0.0000

Data Index: 1455366 (Python Code)

Max Activating Token Index: 29

Text #7

Max Range: 4.7713. Min Range: -4.7713

Max Act: 3.4317. Min Act: -0.0000

Data Index: 1436394 (Python Code)

Max Activating Token Index: 230

Text #8

Max Range: 4.7713. Min Range: -4.7713

Max Act: 3.3673. Min Act: -0.0000

Data Index: 1417356 (Python Code)

Max Activating Token Index: 392

Text #9

Max Range: 4.7713. Min Range: -4.7713

Max Act: 3.3914. Min Act: -0.0000

Data Index: 1403091 (Python Code)

Max Activating Token Index: 261

Text #10

Max Range: 4.7713. Min Range: -4.7713

Max Act: 3.5044. Min Act: -0.0000

Data Index: 1392380 (Python Code)

Max Activating Token Index: 174

Text #11

Max Range: 4.7713. Min Range: -4.7713

Max Act: 3.2736. Min Act: -0.0000

Data Index: 1655562 (Python Code)

Max Activating Token Index: 282

Text #12

Max Range: 4.7713. Min Range: -4.7713

Max Act: 3.4095. Min Act: -0.0000

Data Index: 1520897 (Python Code)

Max Activating Token Index: 357

Text #13

Max Range: 4.7713. Min Range: -4.7713

Max Act: 3.2867. Min Act: -0.0000

Data Index: 1499197 (Python Code)

Max Activating Token Index: 752

Text #14

Max Range: 4.7713. Min Range: -4.7713

Max Act: 3.3728. Min Act: -0.0000

Data Index: 1551315 (Python Code)

Max Activating Token Index: 474

Text #15

Max Range: 4.7713. Min Range: -4.7713

Max Act: 3.1776. Min Act: -0.0000

Data Index: 1584588 (Python Code)

Max Activating Token Index: 287

Text #16

Max Range: 4.7713. Min Range: -4.7713

Max Act: 3.1741. Min Act: -0.0000

Data Index: 1404021 (Python Code)

Max Activating Token Index: 514

Text #17

Max Range: 4.7713. Min Range: -4.7713

Max Act: 3.1492. Min Act: -0.0000

Data Index: 1446675 (Python Code)

Max Activating Token Index: 274

Text #18

Max Range: 4.7713. Min Range: -4.7713

Max Act: 3.4621. Min Act: -0.0000

Data Index: 1450385 (Python Code)

Max Activating Token Index: 201

Text #19

Max Range: 4.7713. Min Range: -4.7713

Max Act: 3.2955. Min Act: -0.0000

Data Index: 1513761 (Python Code)

Max Activating Token Index: 408