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

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

Neuron 2888 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2739. Min Range: -0.2739

Max Act: 0.2739. Min Act: -0.0000

Data Index: 561056 (C4 (Web Text))

Max Activating Token Index: 223

Text #1

Max Range: 0.2739. Min Range: -0.2739

Max Act: 0.2495. Min Act: -0.0000

Data Index: 808447 (C4 (Web Text))

Max Activating Token Index: 947

Text #2

Max Range: 0.2739. Min Range: -0.2739

Max Act: 0.2595. Min Act: -0.0000

Data Index: 985026 (C4 (Web Text))

Max Activating Token Index: 875

Text #3

Max Range: 0.2739. Min Range: -0.2739

Max Act: 0.2261. Min Act: -0.0000

Data Index: 491859 (C4 (Web Text))

Max Activating Token Index: 351

Text #4

Max Range: 0.2739. Min Range: -0.2739

Max Act: 0.2062. Min Act: -0.0000

Data Index: 691654 (C4 (Web Text))

Max Activating Token Index: 685

Text #5

Max Range: 0.2739. Min Range: -0.2739

Max Act: 0.2308. Min Act: -0.0000

Data Index: 230462 (C4 (Web Text))

Max Activating Token Index: 905

Text #6

Max Range: 0.2739. Min Range: -0.2739

Max Act: 0.2054. Min Act: -0.0000

Data Index: 861371 (C4 (Web Text))

Max Activating Token Index: 330

Text #7

Max Range: 0.2739. Min Range: -0.2739

Max Act: 0.1851. Min Act: -0.0000

Data Index: 1327611 (C4 (Web Text))

Max Activating Token Index: 44

Text #8

Max Range: 0.2739. Min Range: -0.2739

Max Act: 0.1969. Min Act: -0.0000

Data Index: 1005332 (C4 (Web Text))

Max Activating Token Index: 627

Text #9

Max Range: 0.2739. Min Range: -0.2739

Max Act: 0.1894. Min Act: -0.0000

Data Index: 1170988 (C4 (Web Text))

Max Activating Token Index: 38

Text #10

Max Range: 0.2739. Min Range: -0.2739

Max Act: 0.2005. Min Act: -0.0000

Data Index: 1231367 (C4 (Web Text))

Max Activating Token Index: 368

Text #11

Max Range: 0.2739. Min Range: -0.2739

Max Act: 0.1971. Min Act: -0.0000

Data Index: 121360 (C4 (Web Text))

Max Activating Token Index: 298

Text #12

Max Range: 0.2739. Min Range: -0.2739

Max Act: 0.1826. Min Act: -0.0000

Data Index: 1130297 (C4 (Web Text))

Max Activating Token Index: 109

Text #13

Max Range: 0.2739. Min Range: -0.2739

Max Act: 0.1870. Min Act: -0.0000

Data Index: 497068 (C4 (Web Text))

Max Activating Token Index: 471

Text #14

Max Range: 0.2739. Min Range: -0.2739

Max Act: 0.1811. Min Act: -0.0000

Data Index: 1141170 (C4 (Web Text))

Max Activating Token Index: 961

Text #15

Max Range: 0.2739. Min Range: -0.2739

Max Act: 0.1850. Min Act: -0.0000

Data Index: 1292524 (C4 (Web Text))

Max Activating Token Index: 894

Text #16

Max Range: 0.2739. Min Range: -0.2739

Max Act: 0.1739. Min Act: -0.0000

Data Index: 9690 (C4 (Web Text))

Max Activating Token Index: 789

Text #17

Max Range: 0.2739. Min Range: -0.2739

Max Act: 0.1727. Min Act: -0.0000

Data Index: 824601 (C4 (Web Text))

Max Activating Token Index: 587

Text #18

Max Range: 0.2739. Min Range: -0.2739

Max Act: 0.1713. Min Act: -0.0000

Data Index: 1031410 (C4 (Web Text))

Max Activating Token Index: 865

Text #19

Max Range: 0.2739. Min Range: -0.2739

Max Act: 0.1703. Min Act: -0.0000

Data Index: 621212 (C4 (Web Text))

Max Activating Token Index: 29