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

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

Neuron 2977 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: 1.0306. Min Range: -1.0306

Max Act: 0.9827. Min Act: -0.0000

Data Index: 1494482 (Python Code)

Max Activating Token Index: 222

Text #1

Max Range: 1.0306. Min Range: -1.0306

Max Act: 1.0306. Min Act: -0.0000

Data Index: 1455295 (Python Code)

Max Activating Token Index: 546

Text #2

Max Range: 1.0306. Min Range: -1.0306

Max Act: 0.8812. Min Act: -0.0000

Data Index: 1513709 (Python Code)

Max Activating Token Index: 796

Text #3

Max Range: 1.0306. Min Range: -1.0306

Max Act: 0.9608. Min Act: -0.0000

Data Index: 1647836 (Python Code)

Max Activating Token Index: 781

Text #4

Max Range: 1.0306. Min Range: -1.0306

Max Act: 0.8855. Min Act: -0.0000

Data Index: 1373301 (Python Code)

Max Activating Token Index: 1020

Text #5

Max Range: 1.0306. Min Range: -1.0306

Max Act: 0.8823. Min Act: -0.0000

Data Index: 1435195 (Python Code)

Max Activating Token Index: 948

Text #6

Max Range: 1.0306. Min Range: -1.0306

Max Act: 0.8871. Min Act: -0.0000

Data Index: 1489117 (Python Code)

Max Activating Token Index: 541

Text #7

Max Range: 1.0306. Min Range: -1.0306

Max Act: 0.8386. Min Act: -0.0000

Data Index: 1619972 (Python Code)

Max Activating Token Index: 308

Text #8

Max Range: 1.0306. Min Range: -1.0306

Max Act: 0.8847. Min Act: -0.0000

Data Index: 1386676 (Python Code)

Max Activating Token Index: 442

Text #9

Max Range: 1.0306. Min Range: -1.0306

Max Act: 0.8226. Min Act: -0.0000

Data Index: 1521485 (Python Code)

Max Activating Token Index: 528

Text #10

Max Range: 1.0306. Min Range: -1.0306

Max Act: 0.8342. Min Act: -0.0000

Data Index: 1632675 (Python Code)

Max Activating Token Index: 934

Text #11

Max Range: 1.0306. Min Range: -1.0306

Max Act: 0.7384. Min Act: -0.0000

Data Index: 1364255 (Python Code)

Max Activating Token Index: 303

Text #12

Max Range: 1.0306. Min Range: -1.0306

Max Act: 0.7800. Min Act: -0.0000

Data Index: 1487222 (Python Code)

Max Activating Token Index: 613

Text #13

Max Range: 1.0306. Min Range: -1.0306

Max Act: 0.7478. Min Act: -0.0000

Data Index: 1479481 (Python Code)

Max Activating Token Index: 640

Text #14

Max Range: 1.0306. Min Range: -1.0306

Max Act: 0.7587. Min Act: -0.0000

Data Index: 1519743 (Python Code)

Max Activating Token Index: 317

Text #15

Max Range: 1.0306. Min Range: -1.0306

Max Act: 0.7400. Min Act: -0.0000

Data Index: 1608046 (Python Code)

Max Activating Token Index: 533

Text #16

Max Range: 1.0306. Min Range: -1.0306

Max Act: 0.7065. Min Act: -0.0000

Data Index: 1391712 (Python Code)

Max Activating Token Index: 758

Text #17

Max Range: 1.0306. Min Range: -1.0306

Max Act: 0.7333. Min Act: -0.0000

Data Index: 1405177 (Python Code)

Max Activating Token Index: 407

Text #18

Max Range: 1.0306. Min Range: -1.0306

Max Act: 0.7500. Min Act: -0.0000

Data Index: 1523132 (Python Code)

Max Activating Token Index: 756

Text #19

Max Range: 1.0306. Min Range: -1.0306

Max Act: 0.7456. Min Act: -0.0000

Data Index: 1437688 (Python Code)

Max Activating Token Index: 822