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

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

Neuron 704 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0867. Min Act: -0.0002

Data Index: 1329859 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0757. Min Act: -0.0002

Data Index: 467899 (C4 (Web Text))

Max Activating Token Index: 347

Text #2

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0726. Min Act: -0.0002

Data Index: 160059 (C4 (Web Text))

Max Activating Token Index: 227

Text #3

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0715. Min Act: -0.0003

Data Index: 165345 (C4 (Web Text))

Max Activating Token Index: 364

Text #4

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0680. Min Act: -0.0002

Data Index: 445862 (C4 (Web Text))

Max Activating Token Index: 1005

Text #5

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0645. Min Act: -0.0003

Data Index: 1194491 (C4 (Web Text))

Max Activating Token Index: 84

Text #6

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0623. Min Act: -0.0002

Data Index: 876341 (C4 (Web Text))

Max Activating Token Index: 919

Text #7

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0617. Min Act: -0.0002

Data Index: 1223613 (C4 (Web Text))

Max Activating Token Index: 768

Text #8

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0631. Min Act: -0.0002

Data Index: 214337 (C4 (Web Text))

Max Activating Token Index: 395

Text #9

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0620. Min Act: -0.0002

Data Index: 1300587 (C4 (Web Text))

Max Activating Token Index: 832

Text #10

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0616. Min Act: -0.0002

Data Index: 17641 (C4 (Web Text))

Max Activating Token Index: 180

Text #11

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0613. Min Act: -0.0002

Data Index: 1162661 (C4 (Web Text))

Max Activating Token Index: 830

Text #12

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0591. Min Act: -0.0002

Data Index: 846489 (C4 (Web Text))

Max Activating Token Index: 265

Text #13

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0578. Min Act: -0.0002

Data Index: 972342 (C4 (Web Text))

Max Activating Token Index: 564

Text #14

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0576. Min Act: -0.0003

Data Index: 846564 (C4 (Web Text))

Max Activating Token Index: 250

Text #15

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0556. Min Act: -0.0002

Data Index: 167621 (C4 (Web Text))

Max Activating Token Index: 713

Text #16

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0566. Min Act: -0.0002

Data Index: 275607 (C4 (Web Text))

Max Activating Token Index: 949

Text #17

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0561. Min Act: -0.0002

Data Index: 735942 (C4 (Web Text))

Max Activating Token Index: 684

Text #18

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0560. Min Act: -0.0002

Data Index: 829803 (C4 (Web Text))

Max Activating Token Index: 314

Text #19

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0544. Min Act: -0.0002

Data Index: 1021531 (C4 (Web Text))

Max Activating Token Index: 1011