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

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

Neuron 4079 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: 1.4873. Min Range: -1.4873

Max Act: 1.4873. Min Act: -0.0000

Data Index: 1460040 (Python Code)

Max Activating Token Index: 794

Text #1

Max Range: 1.4873. Min Range: -1.4873

Max Act: 1.3214. Min Act: -0.0000

Data Index: 1443784 (Python Code)

Max Activating Token Index: 439

Text #2

Max Range: 1.4873. Min Range: -1.4873

Max Act: 1.3401. Min Act: -0.0000

Data Index: 1641879 (Python Code)

Max Activating Token Index: 106

Text #3

Max Range: 1.4873. Min Range: -1.4873

Max Act: 1.1673. Min Act: -0.0000

Data Index: 1443450 (Python Code)

Max Activating Token Index: 19

Text #4

Max Range: 1.4873. Min Range: -1.4873

Max Act: 1.1447. Min Act: -0.0000

Data Index: 1453291 (Python Code)

Max Activating Token Index: 331

Text #5

Max Range: 1.4873. Min Range: -1.4873

Max Act: 1.0954. Min Act: -0.0000

Data Index: 1608482 (Python Code)

Max Activating Token Index: 54

Text #6

Max Range: 1.4873. Min Range: -1.4873

Max Act: 1.1498. Min Act: -0.0000

Data Index: 1513214 (Python Code)

Max Activating Token Index: 503

Text #7

Max Range: 1.4873. Min Range: -1.4873

Max Act: 1.0761. Min Act: -0.0000

Data Index: 1647009 (Python Code)

Max Activating Token Index: 217

Text #8

Max Range: 1.4873. Min Range: -1.4873

Max Act: 1.0579. Min Act: -0.0000

Data Index: 1628331 (Python Code)

Max Activating Token Index: 945

Text #9

Max Range: 1.4873. Min Range: -1.4873

Max Act: 0.9895. Min Act: -0.0000

Data Index: 1370850 (Python Code)

Max Activating Token Index: 965

Text #10

Max Range: 1.4873. Min Range: -1.4873

Max Act: 1.0378. Min Act: -0.0000

Data Index: 1640246 (Python Code)

Max Activating Token Index: 76

Text #11

Max Range: 1.4873. Min Range: -1.4873

Max Act: 1.0425. Min Act: -0.0000

Data Index: 1506025 (Python Code)

Max Activating Token Index: 49

Text #12

Max Range: 1.4873. Min Range: -1.4873

Max Act: 1.1145. Min Act: -0.0000

Data Index: 1621560 (Python Code)

Max Activating Token Index: 949

Text #13

Max Range: 1.4873. Min Range: -1.4873

Max Act: 0.9269. Min Act: -0.0000

Data Index: 1438162 (Python Code)

Max Activating Token Index: 167

Text #14

Max Range: 1.4873. Min Range: -1.4873

Max Act: 0.9656. Min Act: -0.0000

Data Index: 1495740 (Python Code)

Max Activating Token Index: 117

Text #15

Max Range: 1.4873. Min Range: -1.4873

Max Act: 1.0099. Min Act: -0.0000

Data Index: 1373888 (Python Code)

Max Activating Token Index: 621

Text #16

Max Range: 1.4873. Min Range: -1.4873

Max Act: 0.9729. Min Act: -0.0000

Data Index: 1638590 (Python Code)

Max Activating Token Index: 652

Text #17

Max Range: 1.4873. Min Range: -1.4873

Max Act: 1.0504. Min Act: -0.0000

Data Index: 1522089 (Python Code)

Max Activating Token Index: 98

Text #18

Max Range: 1.4873. Min Range: -1.4873

Max Act: 1.0400. Min Act: -0.0000

Data Index: 1409046 (Python Code)

Max Activating Token Index: 158

Text #19

Max Range: 1.4873. Min Range: -1.4873

Max Act: 0.9844. Min Act: -0.0000

Data Index: 1582544 (Python Code)

Max Activating Token Index: 885