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

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

Neuron 4400 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0868. Min Range: -0.0868

Max Act: 0.0853. Min Act: -0.0001

Data Index: 1118435 (C4 (Web Text))

Max Activating Token Index: 874

Text #1

Max Range: 0.0868. Min Range: -0.0868

Max Act: 0.0868. Min Act: -0.0001

Data Index: 850181 (C4 (Web Text))

Max Activating Token Index: 498

Text #2

Max Range: 0.0868. Min Range: -0.0868

Max Act: 0.0853. Min Act: -0.0001

Data Index: 1023762 (C4 (Web Text))

Max Activating Token Index: 224

Text #3

Max Range: 0.0868. Min Range: -0.0868

Max Act: 0.0796. Min Act: -0.0001

Data Index: 509463 (C4 (Web Text))

Max Activating Token Index: 545

Text #4

Max Range: 0.0868. Min Range: -0.0868

Max Act: 0.0795. Min Act: -0.0001

Data Index: 454679 (C4 (Web Text))

Max Activating Token Index: 899

Text #5

Max Range: 0.0868. Min Range: -0.0868

Max Act: 0.0766. Min Act: -0.0001

Data Index: 546824 (C4 (Web Text))

Max Activating Token Index: 259

Text #6

Max Range: 0.0868. Min Range: -0.0868

Max Act: 0.0777. Min Act: -0.0001

Data Index: 970050 (C4 (Web Text))

Max Activating Token Index: 242

Text #7

Max Range: 0.0868. Min Range: -0.0868

Max Act: 0.0753. Min Act: -0.0001

Data Index: 8272 (C4 (Web Text))

Max Activating Token Index: 677

Text #8

Max Range: 0.0868. Min Range: -0.0868

Max Act: 0.0691. Min Act: -0.0001

Data Index: 1180120 (C4 (Web Text))

Max Activating Token Index: 417

Text #9

Max Range: 0.0868. Min Range: -0.0868

Max Act: 0.0722. Min Act: -0.0001

Data Index: 350866 (C4 (Web Text))

Max Activating Token Index: 627

Text #10

Max Range: 0.0868. Min Range: -0.0868

Max Act: 0.0807. Min Act: -0.0001

Data Index: 771689 (C4 (Web Text))

Max Activating Token Index: 700

Text #11

Max Range: 0.0868. Min Range: -0.0868

Max Act: 0.0700. Min Act: -0.0001

Data Index: 800668 (C4 (Web Text))

Max Activating Token Index: 417

Text #12

Max Range: 0.0868. Min Range: -0.0868

Max Act: 0.0674. Min Act: -0.0001

Data Index: 297033 (C4 (Web Text))

Max Activating Token Index: 483

Text #13

Max Range: 0.0868. Min Range: -0.0868

Max Act: 0.0658. Min Act: -0.0001

Data Index: 396251 (C4 (Web Text))

Max Activating Token Index: 88

Text #14

Max Range: 0.0868. Min Range: -0.0868

Max Act: 0.0692. Min Act: -0.0001

Data Index: 1206473 (C4 (Web Text))

Max Activating Token Index: 376

Text #15

Max Range: 0.0868. Min Range: -0.0868

Max Act: 0.0696. Min Act: -0.0001

Data Index: 250755 (C4 (Web Text))

Max Activating Token Index: 507

Text #16

Max Range: 0.0868. Min Range: -0.0868

Max Act: 0.0690. Min Act: -0.0001

Data Index: 1023841 (C4 (Web Text))

Max Activating Token Index: 670

Text #17

Max Range: 0.0868. Min Range: -0.0868

Max Act: 0.0664. Min Act: -0.0001

Data Index: 584216 (C4 (Web Text))

Max Activating Token Index: 33

Text #18

Max Range: 0.0868. Min Range: -0.0868

Max Act: 0.0641. Min Act: -0.0001

Data Index: 66343 (C4 (Web Text))

Max Activating Token Index: 743

Text #19

Max Range: 0.0868. Min Range: -0.0868

Max Act: 0.0636. Min Act: -0.0001

Data Index: 1026080 (C4 (Web Text))

Max Activating Token Index: 891