Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3229 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0885. Min Range: -0.0885

Max Act: 0.0867. Min Act: -0.0001

Data Index: 15226 (C4 (Web Text))

Max Activating Token Index: 903

Text #1

Max Range: 0.0885. Min Range: -0.0885

Max Act: 0.0885. Min Act: -0.0001

Data Index: 657985 (C4 (Web Text))

Max Activating Token Index: 850

Text #2

Max Range: 0.0885. Min Range: -0.0885

Max Act: 0.0825. Min Act: -0.0001

Data Index: 375744 (C4 (Web Text))

Max Activating Token Index: 802

Text #3

Max Range: 0.0885. Min Range: -0.0885

Max Act: 0.0865. Min Act: -0.0001

Data Index: 42543 (C4 (Web Text))

Max Activating Token Index: 494

Text #4

Max Range: 0.0885. Min Range: -0.0885

Max Act: 0.0855. Min Act: -0.0001

Data Index: 1342856 (C4 (Web Text))

Max Activating Token Index: 182

Text #5

Max Range: 0.0885. Min Range: -0.0885

Max Act: 0.0808. Min Act: -0.0001

Data Index: 825330 (C4 (Web Text))

Max Activating Token Index: 506

Text #6

Max Range: 0.0885. Min Range: -0.0885

Max Act: 0.0843. Min Act: -0.0001

Data Index: 81106 (C4 (Web Text))

Max Activating Token Index: 431

Text #7

Max Range: 0.0885. Min Range: -0.0885

Max Act: 0.0821. Min Act: -0.0001

Data Index: 113021 (C4 (Web Text))

Max Activating Token Index: 453

Text #8

Max Range: 0.0885. Min Range: -0.0885

Max Act: 0.0728. Min Act: -0.0001

Data Index: 629561 (C4 (Web Text))

Max Activating Token Index: 713

Text #9

Max Range: 0.0885. Min Range: -0.0885

Max Act: 0.0745. Min Act: -0.0001

Data Index: 114561 (C4 (Web Text))

Max Activating Token Index: 414

Text #10

Max Range: 0.0885. Min Range: -0.0885

Max Act: 0.0732. Min Act: -0.0001

Data Index: 1644273 (Python Code)

Max Activating Token Index: 51

Text #11

Max Range: 0.0885. Min Range: -0.0885

Max Act: 0.0710. Min Act: -0.0001

Data Index: 1237323 (C4 (Web Text))

Max Activating Token Index: 736

Text #12

Max Range: 0.0885. Min Range: -0.0885

Max Act: 0.0708. Min Act: -0.0001

Data Index: 319925 (C4 (Web Text))

Max Activating Token Index: 963

Text #13

Max Range: 0.0885. Min Range: -0.0885

Max Act: 0.0706. Min Act: -0.0001

Data Index: 332119 (C4 (Web Text))

Max Activating Token Index: 52

Text #14

Max Range: 0.0885. Min Range: -0.0885

Max Act: 0.0706. Min Act: -0.0001

Data Index: 326538 (C4 (Web Text))

Max Activating Token Index: 479

Text #15

Max Range: 0.0885. Min Range: -0.0885

Max Act: 0.0684. Min Act: -0.0001

Data Index: 882837 (C4 (Web Text))

Max Activating Token Index: 505

Text #16

Max Range: 0.0885. Min Range: -0.0885

Max Act: 0.0696. Min Act: -0.0001

Data Index: 460929 (C4 (Web Text))

Max Activating Token Index: 648

Text #17

Max Range: 0.0885. Min Range: -0.0885

Max Act: 0.0709. Min Act: -0.0001

Data Index: 921741 (C4 (Web Text))

Max Activating Token Index: 612

Text #18

Max Range: 0.0885. Min Range: -0.0885

Max Act: 0.0668. Min Act: -0.0001

Data Index: 1312945 (C4 (Web Text))

Max Activating Token Index: 90

Text #19

Max Range: 0.0885. Min Range: -0.0885

Max Act: 0.0679. Min Act: -0.0001

Data Index: 294060 (C4 (Web Text))

Max Activating Token Index: 494