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

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

Neuron 5205 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0955. Min Range: -0.0955

Max Act: 0.0955. Min Act: -0.0001

Data Index: 422543 (C4 (Web Text))

Max Activating Token Index: 130

Text #1

Max Range: 0.0955. Min Range: -0.0955

Max Act: 0.0843. Min Act: -0.0001

Data Index: 907694 (C4 (Web Text))

Max Activating Token Index: 804

Text #2

Max Range: 0.0955. Min Range: -0.0955

Max Act: 0.0920. Min Act: -0.0001

Data Index: 612109 (C4 (Web Text))

Max Activating Token Index: 955

Text #3

Max Range: 0.0955. Min Range: -0.0955

Max Act: 0.0868. Min Act: -0.0001

Data Index: 49593 (C4 (Web Text))

Max Activating Token Index: 147

Text #4

Max Range: 0.0955. Min Range: -0.0955

Max Act: 0.0860. Min Act: -0.0001

Data Index: 259331 (C4 (Web Text))

Max Activating Token Index: 20

Text #5

Max Range: 0.0955. Min Range: -0.0955

Max Act: 0.0815. Min Act: -0.0001

Data Index: 1022809 (C4 (Web Text))

Max Activating Token Index: 228

Text #6

Max Range: 0.0955. Min Range: -0.0955

Max Act: 0.0854. Min Act: -0.0001

Data Index: 454030 (C4 (Web Text))

Max Activating Token Index: 955

Text #7

Max Range: 0.0955. Min Range: -0.0955

Max Act: 0.0843. Min Act: -0.0001

Data Index: 1041102 (C4 (Web Text))

Max Activating Token Index: 641

Text #8

Max Range: 0.0955. Min Range: -0.0955

Max Act: 0.0823. Min Act: -0.0001

Data Index: 418494 (C4 (Web Text))

Max Activating Token Index: 28

Text #9

Max Range: 0.0955. Min Range: -0.0955

Max Act: 0.0852. Min Act: -0.0001

Data Index: 1071232 (C4 (Web Text))

Max Activating Token Index: 19

Text #10

Max Range: 0.0955. Min Range: -0.0955

Max Act: 0.0878. Min Act: -0.0001

Data Index: 399848 (C4 (Web Text))

Max Activating Token Index: 144

Text #11

Max Range: 0.0955. Min Range: -0.0955

Max Act: 0.0819. Min Act: -0.0001

Data Index: 823572 (C4 (Web Text))

Max Activating Token Index: 636

Text #12

Max Range: 0.0955. Min Range: -0.0955

Max Act: 0.0806. Min Act: -0.0001

Data Index: 1165395 (C4 (Web Text))

Max Activating Token Index: 912

Text #13

Max Range: 0.0955. Min Range: -0.0955

Max Act: 0.0794. Min Act: -0.0001

Data Index: 356106 (C4 (Web Text))

Max Activating Token Index: 490

Text #14

Max Range: 0.0955. Min Range: -0.0955

Max Act: 0.0815. Min Act: -0.0001

Data Index: 884617 (C4 (Web Text))

Max Activating Token Index: 449

Text #15

Max Range: 0.0955. Min Range: -0.0955

Max Act: 0.0798. Min Act: -0.0001

Data Index: 1010332 (C4 (Web Text))

Max Activating Token Index: 812

Text #16

Max Range: 0.0955. Min Range: -0.0955

Max Act: 0.0793. Min Act: -0.0001

Data Index: 1324361 (C4 (Web Text))

Max Activating Token Index: 847

Text #17

Max Range: 0.0955. Min Range: -0.0955

Max Act: 0.0846. Min Act: -0.0001

Data Index: 654262 (C4 (Web Text))

Max Activating Token Index: 270

Text #18

Max Range: 0.0955. Min Range: -0.0955

Max Act: 0.0779. Min Act: -0.0001

Data Index: 1073476 (C4 (Web Text))

Max Activating Token Index: 488

Text #19

Max Range: 0.0955. Min Range: -0.0955

Max Act: 0.0840. Min Act: -0.0001

Data Index: 106999 (C4 (Web Text))

Max Activating Token Index: 309