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

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

Neuron 3354 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: 1.0568. Min Range: -1.0568

Max Act: 1.0568. Min Act: -0.0002

Data Index: 934691 (C4 (Web Text))

Max Activating Token Index: 382

Text #1

Max Range: 1.0568. Min Range: -1.0568

Max Act: 1.0503. Min Act: -0.0002

Data Index: 732493 (C4 (Web Text))

Max Activating Token Index: 496

Text #2

Max Range: 1.0568. Min Range: -1.0568

Max Act: 1.0546. Min Act: -0.0002

Data Index: 1232939 (C4 (Web Text))

Max Activating Token Index: 696

Text #3

Max Range: 1.0568. Min Range: -1.0568

Max Act: 1.0205. Min Act: -0.0002

Data Index: 461495 (C4 (Web Text))

Max Activating Token Index: 420

Text #4

Max Range: 1.0568. Min Range: -1.0568

Max Act: 1.0230. Min Act: -0.0002

Data Index: 1000799 (C4 (Web Text))

Max Activating Token Index: 689

Text #5

Max Range: 1.0568. Min Range: -1.0568

Max Act: 1.0180. Min Act: -0.0003

Data Index: 364437 (C4 (Web Text))

Max Activating Token Index: 173

Text #6

Max Range: 1.0568. Min Range: -1.0568

Max Act: 0.9892. Min Act: -0.0002

Data Index: 1019001 (C4 (Web Text))

Max Activating Token Index: 876

Text #7

Max Range: 1.0568. Min Range: -1.0568

Max Act: 0.9845. Min Act: -0.0002

Data Index: 296893 (C4 (Web Text))

Max Activating Token Index: 351

Text #8

Max Range: 1.0568. Min Range: -1.0568

Max Act: 0.9855. Min Act: -0.0002

Data Index: 672968 (C4 (Web Text))

Max Activating Token Index: 870

Text #9

Max Range: 1.0568. Min Range: -1.0568

Max Act: 0.9754. Min Act: -0.0002

Data Index: 101978 (C4 (Web Text))

Max Activating Token Index: 837

Text #10

Max Range: 1.0568. Min Range: -1.0568

Max Act: 0.9725. Min Act: -0.0002

Data Index: 724640 (C4 (Web Text))

Max Activating Token Index: 59

Text #11

Max Range: 1.0568. Min Range: -1.0568

Max Act: 0.9716. Min Act: -0.0002

Data Index: 832709 (C4 (Web Text))

Max Activating Token Index: 49

Text #12

Max Range: 1.0568. Min Range: -1.0568

Max Act: 0.9798. Min Act: -0.0002

Data Index: 429581 (C4 (Web Text))

Max Activating Token Index: 157

Text #13

Max Range: 1.0568. Min Range: -1.0568

Max Act: 0.9723. Min Act: -0.0002

Data Index: 1031078 (C4 (Web Text))

Max Activating Token Index: 488

Text #14

Max Range: 1.0568. Min Range: -1.0568

Max Act: 0.9670. Min Act: -0.0002

Data Index: 166946 (C4 (Web Text))

Max Activating Token Index: 655

Text #15

Max Range: 1.0568. Min Range: -1.0568

Max Act: 0.9719. Min Act: -0.0002

Data Index: 404052 (C4 (Web Text))

Max Activating Token Index: 226

Text #16

Max Range: 1.0568. Min Range: -1.0568

Max Act: 0.9436. Min Act: -0.0003

Data Index: 1349452 (C4 (Web Text))

Max Activating Token Index: 486

Text #17

Max Range: 1.0568. Min Range: -1.0568

Max Act: 0.9510. Min Act: -0.0002

Data Index: 856671 (C4 (Web Text))

Max Activating Token Index: 58

Text #18

Max Range: 1.0568. Min Range: -1.0568

Max Act: 0.9568. Min Act: -0.0002

Data Index: 840845 (C4 (Web Text))

Max Activating Token Index: 76

Text #19

Max Range: 1.0568. Min Range: -1.0568

Max Act: 0.9504. Min Act: -0.0002

Data Index: 161800 (C4 (Web Text))

Max Activating Token Index: 78