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

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

Neuron 4576 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.3666. Min Range: -5.3666

Max Act: 5.3194. Min Act: -0.0000

Data Index: 1624502 (Python Code)

Max Activating Token Index: 961

Text #1

Max Range: 5.3666. Min Range: -5.3666

Max Act: 5.3666. Min Act: -0.0000

Data Index: 1417584 (Python Code)

Max Activating Token Index: 754

Text #2

Max Range: 5.3666. Min Range: -5.3666

Max Act: 5.1398. Min Act: -0.0000

Data Index: 1512539 (Python Code)

Max Activating Token Index: 989

Text #3

Max Range: 5.3666. Min Range: -5.3666

Max Act: 5.1026. Min Act: -0.0000

Data Index: 1517944 (Python Code)

Max Activating Token Index: 901

Text #4

Max Range: 5.3666. Min Range: -5.3666

Max Act: 5.1575. Min Act: -0.0000

Data Index: 1363553 (Python Code)

Max Activating Token Index: 169

Text #5

Max Range: 5.3666. Min Range: -5.3666

Max Act: 5.1376. Min Act: -0.0000

Data Index: 1636236 (Python Code)

Max Activating Token Index: 364

Text #6

Max Range: 5.3666. Min Range: -5.3666

Max Act: 4.9456. Min Act: -0.0000

Data Index: 1375144 (Python Code)

Max Activating Token Index: 511

Text #7

Max Range: 5.3666. Min Range: -5.3666

Max Act: 4.9741. Min Act: -0.0000

Data Index: 1583128 (Python Code)

Max Activating Token Index: 137

Text #8

Max Range: 5.3666. Min Range: -5.3666

Max Act: 4.5313. Min Act: -0.0000

Data Index: 1610317 (Python Code)

Max Activating Token Index: 981

Text #9

Max Range: 5.3666. Min Range: -5.3666

Max Act: 4.8871. Min Act: -0.0000

Data Index: 427507 (C4 (Web Text))

Max Activating Token Index: 574

Text #10

Max Range: 5.3666. Min Range: -5.3666

Max Act: 4.3419. Min Act: -0.0000

Data Index: 1577454 (Python Code)

Max Activating Token Index: 77

Text #11

Max Range: 5.3666. Min Range: -5.3666

Max Act: 4.5587. Min Act: -0.0000

Data Index: 1545848 (Python Code)

Max Activating Token Index: 698

Text #12

Max Range: 5.3666. Min Range: -5.3666

Max Act: 4.6859. Min Act: -0.0000

Data Index: 1587682 (Python Code)

Max Activating Token Index: 547

Text #13

Max Range: 5.3666. Min Range: -5.3666

Max Act: 4.5165. Min Act: -0.0000

Data Index: 1372554 (Python Code)

Max Activating Token Index: 420

Text #14

Max Range: 5.3666. Min Range: -5.3666

Max Act: 4.6339. Min Act: -0.0000

Data Index: 1443966 (Python Code)

Max Activating Token Index: 182

Text #15

Max Range: 5.3666. Min Range: -5.3666

Max Act: 4.6630. Min Act: -0.0000

Data Index: 1557968 (Python Code)

Max Activating Token Index: 728

Text #16

Max Range: 5.3666. Min Range: -5.3666

Max Act: 4.4105. Min Act: -0.0000

Data Index: 1318092 (C4 (Web Text))

Max Activating Token Index: 148

Text #17

Max Range: 5.3666. Min Range: -5.3666

Max Act: 4.1767. Min Act: -0.0000

Data Index: 1626508 (Python Code)

Max Activating Token Index: 953

Text #18

Max Range: 5.3666. Min Range: -5.3666

Max Act: 4.1683. Min Act: -0.0000

Data Index: 1432769 (Python Code)

Max Activating Token Index: 636

Text #19

Max Range: 5.3666. Min Range: -5.3666

Max Act: 3.8185. Min Act: -0.0000

Data Index: 1501681 (Python Code)

Max Activating Token Index: 998