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

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

Neuron 1622 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4318. Min Range: -3.4318

Max Act: 3.4318. Min Act: -0.0000

Data Index: 1613528 (Python Code)

Max Activating Token Index: 483

Text #1

Max Range: 3.4318. Min Range: -3.4318

Max Act: 3.1035. Min Act: -0.0000

Data Index: 1426625 (Python Code)

Max Activating Token Index: 263

Text #2

Max Range: 3.4318. Min Range: -3.4318

Max Act: 2.9388. Min Act: -0.0000

Data Index: 1513471 (Python Code)

Max Activating Token Index: 705

Text #3

Max Range: 3.4318. Min Range: -3.4318

Max Act: 2.9465. Min Act: -0.0000

Data Index: 1529830 (Python Code)

Max Activating Token Index: 817

Text #4

Max Range: 3.4318. Min Range: -3.4318

Max Act: 2.9304. Min Act: -0.0000

Data Index: 1531447 (Python Code)

Max Activating Token Index: 857

Text #5

Max Range: 3.4318. Min Range: -3.4318

Max Act: 2.9099. Min Act: -0.0000

Data Index: 1522986 (Python Code)

Max Activating Token Index: 810

Text #6

Max Range: 3.4318. Min Range: -3.4318

Max Act: 2.8859. Min Act: -0.0000

Data Index: 1545859 (Python Code)

Max Activating Token Index: 888

Text #7

Max Range: 3.4318. Min Range: -3.4318

Max Act: 2.6601. Min Act: -0.0000

Data Index: 1415969 (Python Code)

Max Activating Token Index: 477

Text #8

Max Range: 3.4318. Min Range: -3.4318

Max Act: 2.8004. Min Act: -0.0000

Data Index: 1495453 (Python Code)

Max Activating Token Index: 512

Text #9

Max Range: 3.4318. Min Range: -3.4318

Max Act: 3.2143. Min Act: -0.0000

Data Index: 1528519 (Python Code)

Max Activating Token Index: 779

Text #10

Max Range: 3.4318. Min Range: -3.4318

Max Act: 2.8739. Min Act: -0.0000

Data Index: 1467448 (Python Code)

Max Activating Token Index: 872

Text #11

Max Range: 3.4318. Min Range: -3.4318

Max Act: 2.7447. Min Act: -0.0000

Data Index: 1631212 (Python Code)

Max Activating Token Index: 916

Text #12

Max Range: 3.4318. Min Range: -3.4318

Max Act: 2.5981. Min Act: -0.0000

Data Index: 1560382 (Python Code)

Max Activating Token Index: 961

Text #13

Max Range: 3.4318. Min Range: -3.4318

Max Act: 2.6821. Min Act: -0.0000

Data Index: 1589792 (Python Code)

Max Activating Token Index: 531

Text #14

Max Range: 3.4318. Min Range: -3.4318

Max Act: 2.6778. Min Act: -0.0000

Data Index: 1572259 (Python Code)

Max Activating Token Index: 365

Text #15

Max Range: 3.4318. Min Range: -3.4318

Max Act: 2.6200. Min Act: -0.0000

Data Index: 1619813 (Python Code)

Max Activating Token Index: 869

Text #16

Max Range: 3.4318. Min Range: -3.4318

Max Act: 2.6902. Min Act: -0.0000

Data Index: 1617323 (Python Code)

Max Activating Token Index: 224

Text #17

Max Range: 3.4318. Min Range: -3.4318

Max Act: 2.5277. Min Act: -0.0000

Data Index: 1497685 (Python Code)

Max Activating Token Index: 697

Text #18

Max Range: 3.4318. Min Range: -3.4318

Max Act: 2.6781. Min Act: -0.0000

Data Index: 1554649 (Python Code)

Max Activating Token Index: 323

Text #19

Max Range: 3.4318. Min Range: -3.4318

Max Act: 2.5025. Min Act: -0.0000

Data Index: 1401696 (Python Code)

Max Activating Token Index: 363