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

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

Neuron 4237 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0766. Min Range: -0.0766

Max Act: 0.0709. Min Act: -0.0002

Data Index: 742498 (C4 (Web Text))

Max Activating Token Index: 214

Text #1

Max Range: 0.0766. Min Range: -0.0766

Max Act: 0.0700. Min Act: -0.0002

Data Index: 829967 (C4 (Web Text))

Max Activating Token Index: 21

Text #2

Max Range: 0.0766. Min Range: -0.0766

Max Act: 0.0766. Min Act: -0.0002

Data Index: 1053882 (C4 (Web Text))

Max Activating Token Index: 454

Text #3

Max Range: 0.0766. Min Range: -0.0766

Max Act: 0.0766. Min Act: -0.0002

Data Index: 1272350 (C4 (Web Text))

Max Activating Token Index: 429

Text #4

Max Range: 0.0766. Min Range: -0.0766

Max Act: 0.0741. Min Act: -0.0002

Data Index: 483364 (C4 (Web Text))

Max Activating Token Index: 301

Text #5

Max Range: 0.0766. Min Range: -0.0766

Max Act: 0.0705. Min Act: -0.0002

Data Index: 386324 (C4 (Web Text))

Max Activating Token Index: 119

Text #6

Max Range: 0.0766. Min Range: -0.0766

Max Act: 0.0643. Min Act: -0.0002

Data Index: 100713 (C4 (Web Text))

Max Activating Token Index: 769

Text #7

Max Range: 0.0766. Min Range: -0.0766

Max Act: 0.0663. Min Act: -0.0002

Data Index: 1014241 (C4 (Web Text))

Max Activating Token Index: 814

Text #8

Max Range: 0.0766. Min Range: -0.0766

Max Act: 0.0678. Min Act: -0.0002

Data Index: 731282 (C4 (Web Text))

Max Activating Token Index: 304

Text #9

Max Range: 0.0766. Min Range: -0.0766

Max Act: 0.0570. Min Act: -0.0002

Data Index: 427034 (C4 (Web Text))

Max Activating Token Index: 606

Text #10

Max Range: 0.0766. Min Range: -0.0766

Max Act: 0.0714. Min Act: -0.0002

Data Index: 673668 (C4 (Web Text))

Max Activating Token Index: 771

Text #11

Max Range: 0.0766. Min Range: -0.0766

Max Act: 0.0692. Min Act: -0.0002

Data Index: 823842 (C4 (Web Text))

Max Activating Token Index: 444

Text #12

Max Range: 0.0766. Min Range: -0.0766

Max Act: 0.0593. Min Act: -0.0002

Data Index: 874180 (C4 (Web Text))

Max Activating Token Index: 672

Text #13

Max Range: 0.0766. Min Range: -0.0766

Max Act: 0.0639. Min Act: -0.0002

Data Index: 1329265 (C4 (Web Text))

Max Activating Token Index: 135

Text #14

Max Range: 0.0766. Min Range: -0.0766

Max Act: 0.0660. Min Act: -0.0002

Data Index: 785844 (C4 (Web Text))

Max Activating Token Index: 33

Text #15

Max Range: 0.0766. Min Range: -0.0766

Max Act: 0.0647. Min Act: -0.0002

Data Index: 324817 (C4 (Web Text))

Max Activating Token Index: 527

Text #16

Max Range: 0.0766. Min Range: -0.0766

Max Act: 0.0651. Min Act: -0.0002

Data Index: 1277812 (C4 (Web Text))

Max Activating Token Index: 799

Text #17

Max Range: 0.0766. Min Range: -0.0766

Max Act: 0.0643. Min Act: -0.0002

Data Index: 547708 (C4 (Web Text))

Max Activating Token Index: 909

Text #18

Max Range: 0.0766. Min Range: -0.0766

Max Act: 0.0666. Min Act: -0.0002

Data Index: 333930 (C4 (Web Text))

Max Activating Token Index: 386

Text #19

Max Range: 0.0766. Min Range: -0.0766

Max Act: 0.0661. Min Act: -0.0002

Data Index: 1138597 (C4 (Web Text))

Max Activating Token Index: 904