Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2567 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0897. Min Range: -0.0897

Max Act: 0.0897. Min Act: -0.0001

Data Index: 394538 (C4 (Web Text))

Max Activating Token Index: 386

Text #1

Max Range: 0.0897. Min Range: -0.0897

Max Act: 0.0861. Min Act: -0.0001

Data Index: 233778 (C4 (Web Text))

Max Activating Token Index: 159

Text #2

Max Range: 0.0897. Min Range: -0.0897

Max Act: 0.0885. Min Act: -0.0001

Data Index: 509433 (C4 (Web Text))

Max Activating Token Index: 965

Text #3

Max Range: 0.0897. Min Range: -0.0897

Max Act: 0.0808. Min Act: -0.0001

Data Index: 355425 (C4 (Web Text))

Max Activating Token Index: 410

Text #4

Max Range: 0.0897. Min Range: -0.0897

Max Act: 0.0812. Min Act: -0.0001

Data Index: 1162768 (C4 (Web Text))

Max Activating Token Index: 830

Text #5

Max Range: 0.0897. Min Range: -0.0897

Max Act: 0.0814. Min Act: -0.0001

Data Index: 888229 (C4 (Web Text))

Max Activating Token Index: 155

Text #6

Max Range: 0.0897. Min Range: -0.0897

Max Act: 0.0783. Min Act: -0.0001

Data Index: 1201186 (C4 (Web Text))

Max Activating Token Index: 889

Text #7

Max Range: 0.0897. Min Range: -0.0897

Max Act: 0.0794. Min Act: -0.0001

Data Index: 72071 (C4 (Web Text))

Max Activating Token Index: 697

Text #8

Max Range: 0.0897. Min Range: -0.0897

Max Act: 0.0798. Min Act: -0.0001

Data Index: 808893 (C4 (Web Text))

Max Activating Token Index: 291

Text #9

Max Range: 0.0897. Min Range: -0.0897

Max Act: 0.0778. Min Act: -0.0001

Data Index: 235029 (C4 (Web Text))

Max Activating Token Index: 521

Text #10

Max Range: 0.0897. Min Range: -0.0897

Max Act: 0.0750. Min Act: -0.0001

Data Index: 634403 (C4 (Web Text))

Max Activating Token Index: 249

Text #11

Max Range: 0.0897. Min Range: -0.0897

Max Act: 0.0715. Min Act: -0.0001

Data Index: 500428 (C4 (Web Text))

Max Activating Token Index: 228

Text #12

Max Range: 0.0897. Min Range: -0.0897

Max Act: 0.0665. Min Act: -0.0001

Data Index: 1198619 (C4 (Web Text))

Max Activating Token Index: 715

Text #13

Max Range: 0.0897. Min Range: -0.0897

Max Act: 0.0699. Min Act: -0.0001

Data Index: 513401 (C4 (Web Text))

Max Activating Token Index: 244

Text #14

Max Range: 0.0897. Min Range: -0.0897

Max Act: 0.0723. Min Act: -0.0001

Data Index: 119285 (C4 (Web Text))

Max Activating Token Index: 128

Text #15

Max Range: 0.0897. Min Range: -0.0897

Max Act: 0.0650. Min Act: -0.0001

Data Index: 678315 (C4 (Web Text))

Max Activating Token Index: 755

Text #16

Max Range: 0.0897. Min Range: -0.0897

Max Act: 0.0776. Min Act: -0.0001

Data Index: 689826 (C4 (Web Text))

Max Activating Token Index: 938

Text #17

Max Range: 0.0897. Min Range: -0.0897

Max Act: 0.0699. Min Act: -0.0001

Data Index: 21289 (C4 (Web Text))

Max Activating Token Index: 838

Text #18

Max Range: 0.0897. Min Range: -0.0897

Max Act: 0.0686. Min Act: -0.0001

Data Index: 1039305 (C4 (Web Text))

Max Activating Token Index: 155

Text #19

Max Range: 0.0897. Min Range: -0.0897

Max Act: 0.0708. Min Act: -0.0001

Data Index: 1350113 (C4 (Web Text))

Max Activating Token Index: 768