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

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

Neuron 4658 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6714. Min Range: -0.6714

Max Act: 0.6714. Min Act: -0.0001

Data Index: 1311919 (C4 (Web Text))

Max Activating Token Index: 22

Text #1

Max Range: 0.6714. Min Range: -0.6714

Max Act: 0.6494. Min Act: -0.0001

Data Index: 1294463 (C4 (Web Text))

Max Activating Token Index: 262

Text #2

Max Range: 0.6714. Min Range: -0.6714

Max Act: 0.6416. Min Act: -0.0001

Data Index: 176409 (C4 (Web Text))

Max Activating Token Index: 419

Text #3

Max Range: 0.6714. Min Range: -0.6714

Max Act: 0.5540. Min Act: -0.0001

Data Index: 476011 (C4 (Web Text))

Max Activating Token Index: 531

Text #4

Max Range: 0.6714. Min Range: -0.6714

Max Act: 0.6051. Min Act: -0.0001

Data Index: 1002216 (C4 (Web Text))

Max Activating Token Index: 176

Text #5

Max Range: 0.6714. Min Range: -0.6714

Max Act: 0.5818. Min Act: -0.0001

Data Index: 682009 (C4 (Web Text))

Max Activating Token Index: 77

Text #6

Max Range: 0.6714. Min Range: -0.6714

Max Act: 0.5838. Min Act: -0.0001

Data Index: 295362 (C4 (Web Text))

Max Activating Token Index: 166

Text #7

Max Range: 0.6714. Min Range: -0.6714

Max Act: 0.5588. Min Act: -0.0001

Data Index: 587394 (C4 (Web Text))

Max Activating Token Index: 160

Text #8

Max Range: 0.6714. Min Range: -0.6714

Max Act: 0.4868. Min Act: -0.0001

Data Index: 984771 (C4 (Web Text))

Max Activating Token Index: 912

Text #9

Max Range: 0.6714. Min Range: -0.6714

Max Act: 0.6069. Min Act: -0.0001

Data Index: 692699 (C4 (Web Text))

Max Activating Token Index: 722

Text #10

Max Range: 0.6714. Min Range: -0.6714

Max Act: 0.5061. Min Act: -0.0001

Data Index: 269151 (C4 (Web Text))

Max Activating Token Index: 63

Text #11

Max Range: 0.6714. Min Range: -0.6714

Max Act: 0.6072. Min Act: -0.0001

Data Index: 974696 (C4 (Web Text))

Max Activating Token Index: 379

Text #12

Max Range: 0.6714. Min Range: -0.6714

Max Act: 0.5354. Min Act: -0.0001

Data Index: 616378 (C4 (Web Text))

Max Activating Token Index: 969

Text #13

Max Range: 0.6714. Min Range: -0.6714

Max Act: 0.6049. Min Act: -0.0001

Data Index: 336280 (C4 (Web Text))

Max Activating Token Index: 149

Text #14

Max Range: 0.6714. Min Range: -0.6714

Max Act: 0.5357. Min Act: -0.0001

Data Index: 867956 (C4 (Web Text))

Max Activating Token Index: 415

Text #15

Max Range: 0.6714. Min Range: -0.6714

Max Act: 0.6011. Min Act: -0.0001

Data Index: 406399 (C4 (Web Text))

Max Activating Token Index: 657

Text #16

Max Range: 0.6714. Min Range: -0.6714

Max Act: 0.5624. Min Act: -0.0001

Data Index: 1141287 (C4 (Web Text))

Max Activating Token Index: 996

Text #17

Max Range: 0.6714. Min Range: -0.6714

Max Act: 0.5561. Min Act: -0.0001

Data Index: 1308859 (C4 (Web Text))

Max Activating Token Index: 687

Text #18

Max Range: 0.6714. Min Range: -0.6714

Max Act: 0.4904. Min Act: -0.0001

Data Index: 642098 (C4 (Web Text))

Max Activating Token Index: 180

Text #19

Max Range: 0.6714. Min Range: -0.6714

Max Act: 0.5407. Min Act: -0.0001

Data Index: 1169705 (C4 (Web Text))

Max Activating Token Index: 158