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

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

Neuron 1851 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0766. Min Range: -0.0766

Max Act: 0.0766. Min Act: -0.0000

Data Index: 1311036 (C4 (Web Text))

Max Activating Token Index: 153

Text #1

Max Range: 0.0766. Min Range: -0.0766

Max Act: 0.0735. Min Act: -0.0000

Data Index: 795530 (C4 (Web Text))

Max Activating Token Index: 622

Text #2

Max Range: 0.0766. Min Range: -0.0766

Max Act: 0.0719. Min Act: -0.0000

Data Index: 136938 (C4 (Web Text))

Max Activating Token Index: 264

Text #3

Max Range: 0.0766. Min Range: -0.0766

Max Act: 0.0680. Min Act: -0.0000

Data Index: 738043 (C4 (Web Text))

Max Activating Token Index: 203

Text #4

Max Range: 0.0766. Min Range: -0.0766

Max Act: 0.0641. Min Act: -0.0000

Data Index: 928583 (C4 (Web Text))

Max Activating Token Index: 289

Text #5

Max Range: 0.0766. Min Range: -0.0766

Max Act: 0.0663. Min Act: -0.0000

Data Index: 812990 (C4 (Web Text))

Max Activating Token Index: 676

Text #6

Max Range: 0.0766. Min Range: -0.0766

Max Act: 0.0652. Min Act: -0.0000

Data Index: 1254993 (C4 (Web Text))

Max Activating Token Index: 133

Text #7

Max Range: 0.0766. Min Range: -0.0766

Max Act: 0.0632. Min Act: -0.0000

Data Index: 193769 (C4 (Web Text))

Max Activating Token Index: 453

Text #8

Max Range: 0.0766. Min Range: -0.0766

Max Act: 0.0650. Min Act: -0.0000

Data Index: 709036 (C4 (Web Text))

Max Activating Token Index: 672

Text #9

Max Range: 0.0766. Min Range: -0.0766

Max Act: 0.0613. Min Act: -0.0000

Data Index: 91647 (C4 (Web Text))

Max Activating Token Index: 875

Text #10

Max Range: 0.0766. Min Range: -0.0766

Max Act: 0.0642. Min Act: -0.0000

Data Index: 829089 (C4 (Web Text))

Max Activating Token Index: 820

Text #11

Max Range: 0.0766. Min Range: -0.0766

Max Act: 0.0623. Min Act: -0.0000

Data Index: 509833 (C4 (Web Text))

Max Activating Token Index: 315

Text #12

Max Range: 0.0766. Min Range: -0.0766

Max Act: 0.0641. Min Act: -0.0000

Data Index: 238979 (C4 (Web Text))

Max Activating Token Index: 45

Text #13

Max Range: 0.0766. Min Range: -0.0766

Max Act: 0.0643. Min Act: -0.0000

Data Index: 192463 (C4 (Web Text))

Max Activating Token Index: 997

Text #14

Max Range: 0.0766. Min Range: -0.0766

Max Act: 0.0640. Min Act: -0.0000

Data Index: 394918 (C4 (Web Text))

Max Activating Token Index: 752

Text #15

Max Range: 0.0766. Min Range: -0.0766

Max Act: 0.0607. Min Act: -0.0000

Data Index: 420915 (C4 (Web Text))

Max Activating Token Index: 889

Text #16

Max Range: 0.0766. Min Range: -0.0766

Max Act: 0.0660. Min Act: -0.0000

Data Index: 407089 (C4 (Web Text))

Max Activating Token Index: 94

Text #17

Max Range: 0.0766. Min Range: -0.0766

Max Act: 0.0632. Min Act: -0.0000

Data Index: 1167325 (C4 (Web Text))

Max Activating Token Index: 830

Text #18

Max Range: 0.0766. Min Range: -0.0766

Max Act: 0.0605. Min Act: -0.0000

Data Index: 696869 (C4 (Web Text))

Max Activating Token Index: 158

Text #19

Max Range: 0.0766. Min Range: -0.0766

Max Act: 0.0651. Min Act: -0.0000

Data Index: 721333 (C4 (Web Text))

Max Activating Token Index: 311