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

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

Neuron 4329 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.2912. Min Range: -2.2912

Max Act: 2.1612. Min Act: -0.0000

Data Index: 1479589 (Python Code)

Max Activating Token Index: 755

Text #1

Max Range: 2.2912. Min Range: -2.2912

Max Act: 2.2912. Min Act: -0.0000

Data Index: 1565996 (Python Code)

Max Activating Token Index: 546

Text #2

Max Range: 2.2912. Min Range: -2.2912

Max Act: 2.0615. Min Act: -0.0000

Data Index: 1381019 (Python Code)

Max Activating Token Index: 133

Text #3

Max Range: 2.2912. Min Range: -2.2912

Max Act: 2.0416. Min Act: -0.0000

Data Index: 1473211 (Python Code)

Max Activating Token Index: 132

Text #4

Max Range: 2.2912. Min Range: -2.2912

Max Act: 1.9341. Min Act: -0.0000

Data Index: 1584564 (Python Code)

Max Activating Token Index: 301

Text #5

Max Range: 2.2912. Min Range: -2.2912

Max Act: 1.8016. Min Act: -0.0000

Data Index: 1458615 (Python Code)

Max Activating Token Index: 602

Text #6

Max Range: 2.2912. Min Range: -2.2912

Max Act: 1.9086. Min Act: -0.0001

Data Index: 1641390 (Python Code)

Max Activating Token Index: 584

Text #7

Max Range: 2.2912. Min Range: -2.2912

Max Act: 1.8640. Min Act: -0.0000

Data Index: 1593012 (Python Code)

Max Activating Token Index: 149

Text #8

Max Range: 2.2912. Min Range: -2.2912

Max Act: 1.8570. Min Act: -0.0000

Data Index: 1537922 (Python Code)

Max Activating Token Index: 164

Text #9

Max Range: 2.2912. Min Range: -2.2912

Max Act: 1.9321. Min Act: -0.0000

Data Index: 1456227 (Python Code)

Max Activating Token Index: 95

Text #10

Max Range: 2.2912. Min Range: -2.2912

Max Act: 1.7330. Min Act: -0.0000

Data Index: 1640043 (Python Code)

Max Activating Token Index: 742

Text #11

Max Range: 2.2912. Min Range: -2.2912

Max Act: 1.7997. Min Act: -0.0001

Data Index: 1505425 (Python Code)

Max Activating Token Index: 358

Text #12

Max Range: 2.2912. Min Range: -2.2912

Max Act: 1.7625. Min Act: -0.0000

Data Index: 1518806 (Python Code)

Max Activating Token Index: 817

Text #13

Max Range: 2.2912. Min Range: -2.2912

Max Act: 1.7947. Min Act: -0.0000

Data Index: 1527130 (Python Code)

Max Activating Token Index: 283

Text #14

Max Range: 2.2912. Min Range: -2.2912

Max Act: 1.5990. Min Act: -0.0000

Data Index: 1470593 (Python Code)

Max Activating Token Index: 1005

Text #15

Max Range: 2.2912. Min Range: -2.2912

Max Act: 1.7213. Min Act: -0.0000

Data Index: 1627070 (Python Code)

Max Activating Token Index: 673

Text #16

Max Range: 2.2912. Min Range: -2.2912

Max Act: 1.6406. Min Act: -0.0000

Data Index: 1549968 (Python Code)

Max Activating Token Index: 334

Text #17

Max Range: 2.2912. Min Range: -2.2912

Max Act: 1.5900. Min Act: -0.0000

Data Index: 1542358 (Python Code)

Max Activating Token Index: 968

Text #18

Max Range: 2.2912. Min Range: -2.2912

Max Act: 1.8248. Min Act: -0.0000

Data Index: 1423774 (Python Code)

Max Activating Token Index: 723

Text #19

Max Range: 2.2912. Min Range: -2.2912

Max Act: 1.7754. Min Act: -0.0000

Data Index: 1460415 (Python Code)

Max Activating Token Index: 48