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

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

Neuron 1054 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: 0.5661. Min Range: -0.5661

Max Act: 0.5661. Min Act: -0.0000

Data Index: 467697 (C4 (Web Text))

Max Activating Token Index: 968

Text #1

Max Range: 0.5661. Min Range: -0.5661

Max Act: 0.5639. Min Act: -0.0000

Data Index: 1313776 (C4 (Web Text))

Max Activating Token Index: 345

Text #2

Max Range: 0.5661. Min Range: -0.5661

Max Act: 0.4761. Min Act: -0.0000

Data Index: 227216 (C4 (Web Text))

Max Activating Token Index: 982

Text #3

Max Range: 0.5661. Min Range: -0.5661

Max Act: 0.4331. Min Act: -0.0000

Data Index: 1504403 (Python Code)

Max Activating Token Index: 771

Text #4

Max Range: 0.5661. Min Range: -0.5661

Max Act: 0.4006. Min Act: -0.0000

Data Index: 1626836 (Python Code)

Max Activating Token Index: 87

Text #5

Max Range: 0.5661. Min Range: -0.5661

Max Act: 0.3565. Min Act: 0.0001

Data Index: 682010 (C4 (Web Text))

Max Activating Token Index: 340

Text #6

Max Range: 0.5661. Min Range: -0.5661

Max Act: 0.3806. Min Act: -0.0000

Data Index: 1649685 (Python Code)

Max Activating Token Index: 616

Text #7

Max Range: 0.5661. Min Range: -0.5661

Max Act: 0.3645. Min Act: -0.0000

Data Index: 1009294 (C4 (Web Text))

Max Activating Token Index: 576

Text #8

Max Range: 0.5661. Min Range: -0.5661

Max Act: 0.3518. Min Act: -0.0000

Data Index: 644747 (C4 (Web Text))

Max Activating Token Index: 621

Text #9

Max Range: 0.5661. Min Range: -0.5661

Max Act: 0.3380. Min Act: -0.0000

Data Index: 1322145 (C4 (Web Text))

Max Activating Token Index: 598

Text #10

Max Range: 0.5661. Min Range: -0.5661

Max Act: 0.3090. Min Act: -0.0000

Data Index: 327434 (C4 (Web Text))

Max Activating Token Index: 421

Text #11

Max Range: 0.5661. Min Range: -0.5661

Max Act: 0.3255. Min Act: -0.0000

Data Index: 1060313 (C4 (Web Text))

Max Activating Token Index: 53

Text #12

Max Range: 0.5661. Min Range: -0.5661

Max Act: 0.3284. Min Act: 0.0000

Data Index: 584142 (C4 (Web Text))

Max Activating Token Index: 685

Text #13

Max Range: 0.5661. Min Range: -0.5661

Max Act: 0.3070. Min Act: -0.0000

Data Index: 1638497 (Python Code)

Max Activating Token Index: 627

Text #14

Max Range: 0.5661. Min Range: -0.5661

Max Act: 0.3075. Min Act: -0.0000

Data Index: 1592237 (Python Code)

Max Activating Token Index: 29

Text #15

Max Range: 0.5661. Min Range: -0.5661

Max Act: 0.3760. Min Act: 0.0000

Data Index: 1000598 (C4 (Web Text))

Max Activating Token Index: 761

Text #16

Max Range: 0.5661. Min Range: -0.5661

Max Act: 0.2869. Min Act: -0.0000

Data Index: 1564624 (Python Code)

Max Activating Token Index: 432

Text #17

Max Range: 0.5661. Min Range: -0.5661

Max Act: 0.2864. Min Act: -0.0000

Data Index: 1147643 (C4 (Web Text))

Max Activating Token Index: 711

Text #18

Max Range: 0.5661. Min Range: -0.5661

Max Act: 0.2924. Min Act: -0.0000

Data Index: 3929 (C4 (Web Text))

Max Activating Token Index: 817

Text #19

Max Range: 0.5661. Min Range: -0.5661

Max Act: 0.2833. Min Act: -0.0000

Data Index: 1427758 (Python Code)

Max Activating Token Index: 751