Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2028 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.5725. Min Range: -2.5725

Max Act: 2.5725. Min Act: -0.0000

Data Index: 1467047 (Python Code)

Max Activating Token Index: 810

Text #1

Max Range: 2.5725. Min Range: -2.5725

Max Act: 2.3203. Min Act: -0.0000

Data Index: 1574647 (Python Code)

Max Activating Token Index: 828

Text #2

Max Range: 2.5725. Min Range: -2.5725

Max Act: 2.2438. Min Act: -0.0000

Data Index: 1366178 (Python Code)

Max Activating Token Index: 428

Text #3

Max Range: 2.5725. Min Range: -2.5725

Max Act: 2.2424. Min Act: -0.0000

Data Index: 1520133 (Python Code)

Max Activating Token Index: 321

Text #4

Max Range: 2.5725. Min Range: -2.5725

Max Act: 1.9938. Min Act: -0.0000

Data Index: 1437179 (Python Code)

Max Activating Token Index: 545

Text #5

Max Range: 2.5725. Min Range: -2.5725

Max Act: 2.0718. Min Act: -0.0000

Data Index: 1535804 (Python Code)

Max Activating Token Index: 201

Text #6

Max Range: 2.5725. Min Range: -2.5725

Max Act: 2.1389. Min Act: -0.0000

Data Index: 1613648 (Python Code)

Max Activating Token Index: 310

Text #7

Max Range: 2.5725. Min Range: -2.5725

Max Act: 1.9254. Min Act: -0.0000

Data Index: 1452109 (Python Code)

Max Activating Token Index: 484

Text #8

Max Range: 2.5725. Min Range: -2.5725

Max Act: 2.0000. Min Act: -0.0000

Data Index: 1619733 (Python Code)

Max Activating Token Index: 343

Text #9

Max Range: 2.5725. Min Range: -2.5725

Max Act: 1.7406. Min Act: -0.0000

Data Index: 1644883 (Python Code)

Max Activating Token Index: 46

Text #10

Max Range: 2.5725. Min Range: -2.5725

Max Act: 1.8507. Min Act: -0.0000

Data Index: 1430853 (Python Code)

Max Activating Token Index: 238

Text #11

Max Range: 2.5725. Min Range: -2.5725

Max Act: 1.6888. Min Act: -0.0000

Data Index: 1407914 (Python Code)

Max Activating Token Index: 69

Text #12

Max Range: 2.5725. Min Range: -2.5725

Max Act: 1.6519. Min Act: -0.0000

Data Index: 1589710 (Python Code)

Max Activating Token Index: 15

Text #13

Max Range: 2.5725. Min Range: -2.5725

Max Act: 1.5295. Min Act: -0.0000

Data Index: 1381719 (Python Code)

Max Activating Token Index: 55

Text #14

Max Range: 2.5725. Min Range: -2.5725

Max Act: 1.5407. Min Act: -0.0000

Data Index: 1587964 (Python Code)

Max Activating Token Index: 221

Text #15

Max Range: 2.5725. Min Range: -2.5725

Max Act: 1.6123. Min Act: -0.0000

Data Index: 1574741 (Python Code)

Max Activating Token Index: 760

Text #16

Max Range: 2.5725. Min Range: -2.5725

Max Act: 1.5706. Min Act: -0.0000

Data Index: 1462982 (Python Code)

Max Activating Token Index: 952

Text #17

Max Range: 2.5725. Min Range: -2.5725

Max Act: 1.5802. Min Act: -0.0000

Data Index: 1406921 (Python Code)

Max Activating Token Index: 104

Text #18

Max Range: 2.5725. Min Range: -2.5725

Max Act: 1.6422. Min Act: -0.0000

Data Index: 1527444 (Python Code)

Max Activating Token Index: 801

Text #19

Max Range: 2.5725. Min Range: -2.5725

Max Act: 1.4609. Min Act: -0.0000

Data Index: 1460501 (Python Code)

Max Activating Token Index: 546