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

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

Neuron 5400 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: 0.0004. Min Range: -0.0004

Max Act: 0.0004. Min Act: -0.0002

Data Index: 1137607 (C4 (Web Text))

Max Activating Token Index: 742

Text #1

Max Range: 0.0004. Min Range: -0.0004

Max Act: 0.0004. Min Act: -0.0002

Data Index: 1038164 (C4 (Web Text))

Max Activating Token Index: 676

Text #2

Max Range: 0.0004. Min Range: -0.0004

Max Act: 0.0003. Min Act: -0.0002

Data Index: 599663 (C4 (Web Text))

Max Activating Token Index: 617

Text #3

Max Range: 0.0004. Min Range: -0.0004

Max Act: 0.0003. Min Act: -0.0002

Data Index: 802608 (C4 (Web Text))

Max Activating Token Index: 498

Text #4

Max Range: 0.0004. Min Range: -0.0004

Max Act: 0.0003. Min Act: -0.0002

Data Index: 1585791 (Python Code)

Max Activating Token Index: 695

Text #5

Max Range: 0.0004. Min Range: -0.0004

Max Act: 0.0003. Min Act: -0.0002

Data Index: 580921 (C4 (Web Text))

Max Activating Token Index: 554

Text #6

Max Range: 0.0004. Min Range: -0.0004

Max Act: 0.0003. Min Act: -0.0002

Data Index: 568349 (C4 (Web Text))

Max Activating Token Index: 655

Text #7

Max Range: 0.0004. Min Range: -0.0004

Max Act: 0.0003. Min Act: -0.0002

Data Index: 1111024 (C4 (Web Text))

Max Activating Token Index: 608

Text #8

Max Range: 0.0004. Min Range: -0.0004

Max Act: 0.0003. Min Act: -0.0002

Data Index: 1286973 (C4 (Web Text))

Max Activating Token Index: 656

Text #9

Max Range: 0.0004. Min Range: -0.0004

Max Act: 0.0003. Min Act: -0.0002

Data Index: 640491 (C4 (Web Text))

Max Activating Token Index: 563

Text #10

Max Range: 0.0004. Min Range: -0.0004

Max Act: 0.0003. Min Act: -0.0002

Data Index: 1221518 (C4 (Web Text))

Max Activating Token Index: 611

Text #11

Max Range: 0.0004. Min Range: -0.0004

Max Act: 0.0003. Min Act: -0.0002

Data Index: 1011182 (C4 (Web Text))

Max Activating Token Index: 448

Text #12

Max Range: 0.0004. Min Range: -0.0004

Max Act: 0.0003. Min Act: -0.0002

Data Index: 706552 (C4 (Web Text))

Max Activating Token Index: 743

Text #13

Max Range: 0.0004. Min Range: -0.0004

Max Act: 0.0003. Min Act: -0.0002

Data Index: 472759 (C4 (Web Text))

Max Activating Token Index: 540

Text #14

Max Range: 0.0004. Min Range: -0.0004

Max Act: 0.0003. Min Act: -0.0002

Data Index: 61772 (C4 (Web Text))

Max Activating Token Index: 755

Text #15

Max Range: 0.0004. Min Range: -0.0004

Max Act: 0.0003. Min Act: -0.0002

Data Index: 423982 (C4 (Web Text))

Max Activating Token Index: 508

Text #16

Max Range: 0.0004. Min Range: -0.0004

Max Act: 0.0002. Min Act: -0.0002

Data Index: 830351 (C4 (Web Text))

Max Activating Token Index: 774

Text #17

Max Range: 0.0004. Min Range: -0.0004

Max Act: 0.0002. Min Act: -0.0002

Data Index: 1509731 (Python Code)

Max Activating Token Index: 660

Text #18

Max Range: 0.0004. Min Range: -0.0004

Max Act: 0.0002. Min Act: -0.0002

Data Index: 850251 (C4 (Web Text))

Max Activating Token Index: 653

Text #19

Max Range: 0.0004. Min Range: -0.0004

Max Act: 0.0002. Min Act: -0.0002

Data Index: 120216 (C4 (Web Text))

Max Activating Token Index: 525