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

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

Neuron 3343 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: 0.7478. Min Range: -0.7478

Max Act: 0.7478. Min Act: -0.0000

Data Index: 1449699 (Python Code)

Max Activating Token Index: 611

Text #1

Max Range: 0.7478. Min Range: -0.7478

Max Act: 0.7260. Min Act: -0.0000

Data Index: 1593492 (Python Code)

Max Activating Token Index: 717

Text #2

Max Range: 0.7478. Min Range: -0.7478

Max Act: 0.6388. Min Act: -0.0000

Data Index: 1508820 (Python Code)

Max Activating Token Index: 531

Text #3

Max Range: 0.7478. Min Range: -0.7478

Max Act: 0.6793. Min Act: -0.0000

Data Index: 1420280 (Python Code)

Max Activating Token Index: 143

Text #4

Max Range: 0.7478. Min Range: -0.7478

Max Act: 0.5895. Min Act: -0.0000

Data Index: 1475396 (Python Code)

Max Activating Token Index: 973

Text #5

Max Range: 0.7478. Min Range: -0.7478

Max Act: 0.5390. Min Act: -0.0000

Data Index: 1571679 (Python Code)

Max Activating Token Index: 124

Text #6

Max Range: 0.7478. Min Range: -0.7478

Max Act: 0.6020. Min Act: -0.0000

Data Index: 1648703 (Python Code)

Max Activating Token Index: 82

Text #7

Max Range: 0.7478. Min Range: -0.7478

Max Act: 0.5389. Min Act: -0.0000

Data Index: 1426198 (Python Code)

Max Activating Token Index: 413

Text #8

Max Range: 0.7478. Min Range: -0.7478

Max Act: 0.5499. Min Act: -0.0000

Data Index: 1580667 (Python Code)

Max Activating Token Index: 125

Text #9

Max Range: 0.7478. Min Range: -0.7478

Max Act: 0.4962. Min Act: -0.0000

Data Index: 1489178 (Python Code)

Max Activating Token Index: 73

Text #10

Max Range: 0.7478. Min Range: -0.7478

Max Act: 0.5191. Min Act: -0.0000

Data Index: 1533954 (Python Code)

Max Activating Token Index: 16

Text #11

Max Range: 0.7478. Min Range: -0.7478

Max Act: 0.4970. Min Act: -0.0000

Data Index: 1620241 (Python Code)

Max Activating Token Index: 30

Text #12

Max Range: 0.7478. Min Range: -0.7478

Max Act: 0.4470. Min Act: -0.0000

Data Index: 1430409 (Python Code)

Max Activating Token Index: 290

Text #13

Max Range: 0.7478. Min Range: -0.7478

Max Act: 0.4892. Min Act: -0.0000

Data Index: 1372617 (Python Code)

Max Activating Token Index: 591

Text #14

Max Range: 0.7478. Min Range: -0.7478

Max Act: 0.4422. Min Act: -0.0000

Data Index: 1642176 (Python Code)

Max Activating Token Index: 172

Text #15

Max Range: 0.7478. Min Range: -0.7478

Max Act: 0.4448. Min Act: -0.0000

Data Index: 1485901 (Python Code)

Max Activating Token Index: 768

Text #16

Max Range: 0.7478. Min Range: -0.7478

Max Act: 0.4380. Min Act: -0.0000

Data Index: 1471629 (Python Code)

Max Activating Token Index: 293

Text #17

Max Range: 0.7478. Min Range: -0.7478

Max Act: 0.4696. Min Act: -0.0000

Data Index: 1606015 (Python Code)

Max Activating Token Index: 41

Text #18

Max Range: 0.7478. Min Range: -0.7478

Max Act: 0.4513. Min Act: -0.0000

Data Index: 1578862 (Python Code)

Max Activating Token Index: 113

Text #19

Max Range: 0.7478. Min Range: -0.7478

Max Act: 0.4811. Min Act: -0.0000

Data Index: 1544571 (Python Code)

Max Activating Token Index: 12