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

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

Neuron 1213 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: 5.2090. Min Range: -5.2090

Max Act: 5.2090. Min Act: -0.0000

Data Index: 391961 (C4 (Web Text))

Max Activating Token Index: 901

Text #1

Max Range: 5.2090. Min Range: -5.2090

Max Act: 4.2976. Min Act: -0.0000

Data Index: 1120685 (C4 (Web Text))

Max Activating Token Index: 15

Text #2

Max Range: 5.2090. Min Range: -5.2090

Max Act: 4.1820. Min Act: -0.0000

Data Index: 253359 (C4 (Web Text))

Max Activating Token Index: 837

Text #3

Max Range: 5.2090. Min Range: -5.2090

Max Act: 4.5438. Min Act: -0.0000

Data Index: 432535 (C4 (Web Text))

Max Activating Token Index: 252

Text #4

Max Range: 5.2090. Min Range: -5.2090

Max Act: 4.2991. Min Act: -0.0000

Data Index: 724323 (C4 (Web Text))

Max Activating Token Index: 591

Text #5

Max Range: 5.2090. Min Range: -5.2090

Max Act: 4.2201. Min Act: -0.0000

Data Index: 744275 (C4 (Web Text))

Max Activating Token Index: 889

Text #6

Max Range: 5.2090. Min Range: -5.2090

Max Act: 4.1121. Min Act: -0.0000

Data Index: 31409 (C4 (Web Text))

Max Activating Token Index: 9

Text #7

Max Range: 5.2090. Min Range: -5.2090

Max Act: 4.0442. Min Act: -0.0000

Data Index: 939212 (C4 (Web Text))

Max Activating Token Index: 704

Text #8

Max Range: 5.2090. Min Range: -5.2090

Max Act: 4.0258. Min Act: -0.0000

Data Index: 988005 (C4 (Web Text))

Max Activating Token Index: 686

Text #9

Max Range: 5.2090. Min Range: -5.2090

Max Act: 3.9365. Min Act: -0.0000

Data Index: 401074 (C4 (Web Text))

Max Activating Token Index: 535

Text #10

Max Range: 5.2090. Min Range: -5.2090

Max Act: 3.9107. Min Act: -0.0000

Data Index: 361749 (C4 (Web Text))

Max Activating Token Index: 620

Text #11

Max Range: 5.2090. Min Range: -5.2090

Max Act: 3.8308. Min Act: -0.0000

Data Index: 929756 (C4 (Web Text))

Max Activating Token Index: 715

Text #12

Max Range: 5.2090. Min Range: -5.2090

Max Act: 3.4861. Min Act: -0.0000

Data Index: 233076 (C4 (Web Text))

Max Activating Token Index: 268

Text #13

Max Range: 5.2090. Min Range: -5.2090

Max Act: 3.8245. Min Act: -0.0000

Data Index: 1300661 (C4 (Web Text))

Max Activating Token Index: 853

Text #14

Max Range: 5.2090. Min Range: -5.2090

Max Act: 3.9589. Min Act: -0.0000

Data Index: 463497 (C4 (Web Text))

Max Activating Token Index: 752

Text #15

Max Range: 5.2090. Min Range: -5.2090

Max Act: 3.7715. Min Act: -0.0000

Data Index: 612087 (C4 (Web Text))

Max Activating Token Index: 784

Text #16

Max Range: 5.2090. Min Range: -5.2090

Max Act: 3.7696. Min Act: -0.0000

Data Index: 1048038 (C4 (Web Text))

Max Activating Token Index: 89

Text #17

Max Range: 5.2090. Min Range: -5.2090

Max Act: 3.7609. Min Act: -0.0000

Data Index: 967758 (C4 (Web Text))

Max Activating Token Index: 51

Text #18

Max Range: 5.2090. Min Range: -5.2090

Max Act: 3.7677. Min Act: -0.0000

Data Index: 1231696 (C4 (Web Text))

Max Activating Token Index: 946

Text #19

Max Range: 5.2090. Min Range: -5.2090

Max Act: 3.7548. Min Act: -0.0000

Data Index: 1154100 (C4 (Web Text))

Max Activating Token Index: 615