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

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

Neuron 1972 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.6812. Min Range: -0.6812

Max Act: 0.6812. Min Act: -0.0000

Data Index: 165441 (C4 (Web Text))

Max Activating Token Index: 801

Text #1

Max Range: 0.6812. Min Range: -0.6812

Max Act: 0.6219. Min Act: -0.0000

Data Index: 1643742 (Python Code)

Max Activating Token Index: 707

Text #2

Max Range: 0.6812. Min Range: -0.6812

Max Act: 0.6550. Min Act: -0.0000

Data Index: 1512942 (Python Code)

Max Activating Token Index: 903

Text #3

Max Range: 0.6812. Min Range: -0.6812

Max Act: 0.6076. Min Act: -0.0000

Data Index: 792272 (C4 (Web Text))

Max Activating Token Index: 552

Text #4

Max Range: 0.6812. Min Range: -0.6812

Max Act: 0.6234. Min Act: -0.0000

Data Index: 1577540 (Python Code)

Max Activating Token Index: 916

Text #5

Max Range: 0.6812. Min Range: -0.6812

Max Act: 0.6105. Min Act: -0.0000

Data Index: 1552785 (Python Code)

Max Activating Token Index: 981

Text #6

Max Range: 0.6812. Min Range: -0.6812

Max Act: 0.6240. Min Act: -0.0000

Data Index: 1461423 (Python Code)

Max Activating Token Index: 885

Text #7

Max Range: 0.6812. Min Range: -0.6812

Max Act: 0.6327. Min Act: -0.0000

Data Index: 1632894 (Python Code)

Max Activating Token Index: 311

Text #8

Max Range: 0.6812. Min Range: -0.6812

Max Act: 0.6275. Min Act: -0.0000

Data Index: 1656711 (Python Code)

Max Activating Token Index: 924

Text #9

Max Range: 0.6812. Min Range: -0.6812

Max Act: 0.6216. Min Act: -0.0000

Data Index: 218922 (C4 (Web Text))

Max Activating Token Index: 295

Text #10

Max Range: 0.6812. Min Range: -0.6812

Max Act: 0.5645. Min Act: -0.0000

Data Index: 1618802 (Python Code)

Max Activating Token Index: 211

Text #11

Max Range: 0.6812. Min Range: -0.6812

Max Act: 0.6014. Min Act: -0.0000

Data Index: 739153 (C4 (Web Text))

Max Activating Token Index: 929

Text #12

Max Range: 0.6812. Min Range: -0.6812

Max Act: 0.6051. Min Act: -0.0000

Data Index: 310683 (C4 (Web Text))

Max Activating Token Index: 814

Text #13

Max Range: 0.6812. Min Range: -0.6812

Max Act: 0.5960. Min Act: -0.0000

Data Index: 1371404 (Python Code)

Max Activating Token Index: 896

Text #14

Max Range: 0.6812. Min Range: -0.6812

Max Act: 0.5838. Min Act: -0.0000

Data Index: 72528 (C4 (Web Text))

Max Activating Token Index: 445

Text #15

Max Range: 0.6812. Min Range: -0.6812

Max Act: 0.5771. Min Act: -0.0000

Data Index: 1548447 (Python Code)

Max Activating Token Index: 61

Text #16

Max Range: 0.6812. Min Range: -0.6812

Max Act: 0.5541. Min Act: -0.0000

Data Index: 1175875 (C4 (Web Text))

Max Activating Token Index: 552

Text #17

Max Range: 0.6812. Min Range: -0.6812

Max Act: 0.5607. Min Act: -0.0000

Data Index: 682893 (C4 (Web Text))

Max Activating Token Index: 865

Text #18

Max Range: 0.6812. Min Range: -0.6812

Max Act: 0.5913. Min Act: -0.0000

Data Index: 481086 (C4 (Web Text))

Max Activating Token Index: 49

Text #19

Max Range: 0.6812. Min Range: -0.6812

Max Act: 0.5123. Min Act: -0.0000

Data Index: 1594846 (Python Code)

Max Activating Token Index: 144