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

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

Neuron 3478 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2714. Min Range: -0.2714

Max Act: 0.2714. Min Act: -0.0000

Data Index: 1078519 (C4 (Web Text))

Max Activating Token Index: 76

Text #1

Max Range: 0.2714. Min Range: -0.2714

Max Act: 0.2656. Min Act: -0.0000

Data Index: 911198 (C4 (Web Text))

Max Activating Token Index: 28

Text #2

Max Range: 0.2714. Min Range: -0.2714

Max Act: 0.2530. Min Act: -0.0000

Data Index: 1223764 (C4 (Web Text))

Max Activating Token Index: 541

Text #3

Max Range: 0.2714. Min Range: -0.2714

Max Act: 0.2483. Min Act: -0.0000

Data Index: 740543 (C4 (Web Text))

Max Activating Token Index: 780

Text #4

Max Range: 0.2714. Min Range: -0.2714

Max Act: 0.2346. Min Act: 0.0000

Data Index: 508292 (C4 (Web Text))

Max Activating Token Index: 877

Text #5

Max Range: 0.2714. Min Range: -0.2714

Max Act: 0.2113. Min Act: -0.0000

Data Index: 11009 (C4 (Web Text))

Max Activating Token Index: 388

Text #6

Max Range: 0.2714. Min Range: -0.2714

Max Act: 0.2010. Min Act: -0.0000

Data Index: 775023 (C4 (Web Text))

Max Activating Token Index: 42

Text #7

Max Range: 0.2714. Min Range: -0.2714

Max Act: 0.2159. Min Act: -0.0000

Data Index: 1103135 (C4 (Web Text))

Max Activating Token Index: 138

Text #8

Max Range: 0.2714. Min Range: -0.2714

Max Act: 0.2074. Min Act: -0.0000

Data Index: 736922 (C4 (Web Text))

Max Activating Token Index: 892

Text #9

Max Range: 0.2714. Min Range: -0.2714

Max Act: 0.2029. Min Act: -0.0000

Data Index: 613506 (C4 (Web Text))

Max Activating Token Index: 65

Text #10

Max Range: 0.2714. Min Range: -0.2714

Max Act: 0.1941. Min Act: -0.0000

Data Index: 287728 (C4 (Web Text))

Max Activating Token Index: 119

Text #11

Max Range: 0.2714. Min Range: -0.2714

Max Act: 0.1907. Min Act: -0.0000

Data Index: 454168 (C4 (Web Text))

Max Activating Token Index: 668

Text #12

Max Range: 0.2714. Min Range: -0.2714

Max Act: 0.1706. Min Act: -0.0000

Data Index: 102530 (C4 (Web Text))

Max Activating Token Index: 734

Text #13

Max Range: 0.2714. Min Range: -0.2714

Max Act: 0.1934. Min Act: -0.0000

Data Index: 189055 (C4 (Web Text))

Max Activating Token Index: 883

Text #14

Max Range: 0.2714. Min Range: -0.2714

Max Act: 0.1917. Min Act: -0.0000

Data Index: 432993 (C4 (Web Text))

Max Activating Token Index: 79

Text #15

Max Range: 0.2714. Min Range: -0.2714

Max Act: 0.1839. Min Act: -0.0000

Data Index: 845794 (C4 (Web Text))

Max Activating Token Index: 605

Text #16

Max Range: 0.2714. Min Range: -0.2714

Max Act: 0.1700. Min Act: -0.0000

Data Index: 790145 (C4 (Web Text))

Max Activating Token Index: 955

Text #17

Max Range: 0.2714. Min Range: -0.2714

Max Act: 0.1812. Min Act: -0.0000

Data Index: 25576 (C4 (Web Text))

Max Activating Token Index: 238

Text #18

Max Range: 0.2714. Min Range: -0.2714

Max Act: 0.1675. Min Act: -0.0000

Data Index: 177705 (C4 (Web Text))

Max Activating Token Index: 677

Text #19

Max Range: 0.2714. Min Range: -0.2714

Max Act: 0.1844. Min Act: -0.0000

Data Index: 1108224 (C4 (Web Text))

Max Activating Token Index: 341