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

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

Neuron 4152 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: 0.9719. Min Range: -0.9719

Max Act: 0.9719. Min Act: -0.0000

Data Index: 687410 (C4 (Web Text))

Max Activating Token Index: 769

Text #1

Max Range: 0.9719. Min Range: -0.9719

Max Act: 0.8759. Min Act: -0.0000

Data Index: 641012 (C4 (Web Text))

Max Activating Token Index: 579

Text #2

Max Range: 0.9719. Min Range: -0.9719

Max Act: 0.7753. Min Act: -0.0000

Data Index: 1018460 (C4 (Web Text))

Max Activating Token Index: 935

Text #3

Max Range: 0.9719. Min Range: -0.9719

Max Act: 0.7532. Min Act: -0.0000

Data Index: 1145714 (C4 (Web Text))

Max Activating Token Index: 280

Text #4

Max Range: 0.9719. Min Range: -0.9719

Max Act: 0.7382. Min Act: -0.0000

Data Index: 160691 (C4 (Web Text))

Max Activating Token Index: 998

Text #5

Max Range: 0.9719. Min Range: -0.9719

Max Act: 0.7117. Min Act: -0.0000

Data Index: 342044 (C4 (Web Text))

Max Activating Token Index: 32

Text #6

Max Range: 0.9719. Min Range: -0.9719

Max Act: 0.7519. Min Act: -0.0000

Data Index: 1270773 (C4 (Web Text))

Max Activating Token Index: 744

Text #7

Max Range: 0.9719. Min Range: -0.9719

Max Act: 0.6776. Min Act: -0.0000

Data Index: 276025 (C4 (Web Text))

Max Activating Token Index: 25

Text #8

Max Range: 0.9719. Min Range: -0.9719

Max Act: 0.7198. Min Act: -0.0000

Data Index: 789453 (C4 (Web Text))

Max Activating Token Index: 823

Text #9

Max Range: 0.9719. Min Range: -0.9719

Max Act: 0.6727. Min Act: -0.0000

Data Index: 33691 (C4 (Web Text))

Max Activating Token Index: 97

Text #10

Max Range: 0.9719. Min Range: -0.9719

Max Act: 0.7043. Min Act: -0.0000

Data Index: 237816 (C4 (Web Text))

Max Activating Token Index: 814

Text #11

Max Range: 0.9719. Min Range: -0.9719

Max Act: 0.6571. Min Act: -0.0000

Data Index: 712907 (C4 (Web Text))

Max Activating Token Index: 422

Text #12

Max Range: 0.9719. Min Range: -0.9719

Max Act: 0.6767. Min Act: -0.0000

Data Index: 79860 (C4 (Web Text))

Max Activating Token Index: 867

Text #13

Max Range: 0.9719. Min Range: -0.9719

Max Act: 0.6824. Min Act: -0.0000

Data Index: 1070902 (C4 (Web Text))

Max Activating Token Index: 301

Text #14

Max Range: 0.9719. Min Range: -0.9719

Max Act: 0.6535. Min Act: -0.0000

Data Index: 618331 (C4 (Web Text))

Max Activating Token Index: 28

Text #15

Max Range: 0.9719. Min Range: -0.9719

Max Act: 0.6151. Min Act: -0.0000

Data Index: 756713 (C4 (Web Text))

Max Activating Token Index: 783

Text #16

Max Range: 0.9719. Min Range: -0.9719

Max Act: 0.6566. Min Act: -0.0000

Data Index: 1161242 (C4 (Web Text))

Max Activating Token Index: 25

Text #17

Max Range: 0.9719. Min Range: -0.9719

Max Act: 0.6315. Min Act: -0.0000

Data Index: 783077 (C4 (Web Text))

Max Activating Token Index: 165

Text #18

Max Range: 0.9719. Min Range: -0.9719

Max Act: 0.6088. Min Act: -0.0000

Data Index: 973076 (C4 (Web Text))

Max Activating Token Index: 78

Text #19

Max Range: 0.9719. Min Range: -0.9719

Max Act: 0.6278. Min Act: -0.0000

Data Index: 553760 (C4 (Web Text))

Max Activating Token Index: 308