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

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

Neuron 4918 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: 1.7725. Min Range: -1.7725

Max Act: 1.7725. Min Act: -0.0001

Data Index: 1524465 (Python Code)

Max Activating Token Index: 16

Text #1

Max Range: 1.7725. Min Range: -1.7725

Max Act: 1.3754. Min Act: -0.0000

Data Index: 342699 (C4 (Web Text))

Max Activating Token Index: 185

Text #2

Max Range: 1.7725. Min Range: -1.7725

Max Act: 1.4911. Min Act: -0.0001

Data Index: 1605755 (Python Code)

Max Activating Token Index: 891

Text #3

Max Range: 1.7725. Min Range: -1.7725

Max Act: 1.3102. Min Act: -0.0000

Data Index: 1627006 (Python Code)

Max Activating Token Index: 291

Text #4

Max Range: 1.7725. Min Range: -1.7725

Max Act: 1.5509. Min Act: -0.0000

Data Index: 1596662 (Python Code)

Max Activating Token Index: 83

Text #5

Max Range: 1.7725. Min Range: -1.7725

Max Act: 1.2232. Min Act: -0.0001

Data Index: 1392468 (Python Code)

Max Activating Token Index: 822

Text #6

Max Range: 1.7725. Min Range: -1.7725

Max Act: 1.3320. Min Act: -0.0000

Data Index: 782281 (C4 (Web Text))

Max Activating Token Index: 315

Text #7

Max Range: 1.7725. Min Range: -1.7725

Max Act: 1.2715. Min Act: -0.0001

Data Index: 800232 (C4 (Web Text))

Max Activating Token Index: 935

Text #8

Max Range: 1.7725. Min Range: -1.7725

Max Act: 1.1930. Min Act: -0.0000

Data Index: 1482537 (Python Code)

Max Activating Token Index: 836

Text #9

Max Range: 1.7725. Min Range: -1.7725

Max Act: 1.2842. Min Act: -0.0001

Data Index: 1504905 (Python Code)

Max Activating Token Index: 290

Text #10

Max Range: 1.7725. Min Range: -1.7725

Max Act: 1.2931. Min Act: -0.0000

Data Index: 1457618 (Python Code)

Max Activating Token Index: 416

Text #11

Max Range: 1.7725. Min Range: -1.7725

Max Act: 1.2090. Min Act: -0.0001

Data Index: 792906 (C4 (Web Text))

Max Activating Token Index: 670

Text #12

Max Range: 1.7725. Min Range: -1.7725

Max Act: 1.1620. Min Act: -0.0000

Data Index: 1419287 (Python Code)

Max Activating Token Index: 98

Text #13

Max Range: 1.7725. Min Range: -1.7725

Max Act: 1.1959. Min Act: -0.0000

Data Index: 590961 (C4 (Web Text))

Max Activating Token Index: 574

Text #14

Max Range: 1.7725. Min Range: -1.7725

Max Act: 1.1342. Min Act: -0.0000

Data Index: 1433383 (Python Code)

Max Activating Token Index: 745

Text #15

Max Range: 1.7725. Min Range: -1.7725

Max Act: 1.1641. Min Act: -0.0001

Data Index: 366912 (C4 (Web Text))

Max Activating Token Index: 803

Text #16

Max Range: 1.7725. Min Range: -1.7725

Max Act: 1.0791. Min Act: -0.0001

Data Index: 1407618 (Python Code)

Max Activating Token Index: 34

Text #17

Max Range: 1.7725. Min Range: -1.7725

Max Act: 1.0623. Min Act: -0.0001

Data Index: 1652079 (Python Code)

Max Activating Token Index: 825

Text #18

Max Range: 1.7725. Min Range: -1.7725

Max Act: 1.0484. Min Act: -0.0000

Data Index: 1433967 (Python Code)

Max Activating Token Index: 146

Text #19

Max Range: 1.7725. Min Range: -1.7725

Max Act: 0.9470. Min Act: -0.0000

Data Index: 1524458 (Python Code)

Max Activating Token Index: 553