Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3201 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0996. Min Act: -0.0003

Data Index: 14965 (C4 (Web Text))

Max Activating Token Index: 637

Text #1

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0937. Min Act: -0.0003

Data Index: 744817 (C4 (Web Text))

Max Activating Token Index: 579

Text #2

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0933. Min Act: -0.0003

Data Index: 779890 (C4 (Web Text))

Max Activating Token Index: 109

Text #3

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0899. Min Act: -0.0003

Data Index: 894735 (C4 (Web Text))

Max Activating Token Index: 180

Text #4

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0892. Min Act: -0.0003

Data Index: 634649 (C4 (Web Text))

Max Activating Token Index: 683

Text #5

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0841. Min Act: -0.0003

Data Index: 211108 (C4 (Web Text))

Max Activating Token Index: 584

Text #6

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0844. Min Act: -0.0003

Data Index: 1020342 (C4 (Web Text))

Max Activating Token Index: 589

Text #7

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0829. Min Act: -0.0003

Data Index: 775610 (C4 (Web Text))

Max Activating Token Index: 937

Text #8

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0772. Min Act: -0.0003

Data Index: 42470 (C4 (Web Text))

Max Activating Token Index: 275

Text #9

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0781. Min Act: -0.0003

Data Index: 122064 (C4 (Web Text))

Max Activating Token Index: 269

Text #10

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0798. Min Act: -0.0003

Data Index: 427586 (C4 (Web Text))

Max Activating Token Index: 342

Text #11

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0785. Min Act: -0.0003

Data Index: 366095 (C4 (Web Text))

Max Activating Token Index: 104

Text #12

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0775. Min Act: -0.0003

Data Index: 43828 (C4 (Web Text))

Max Activating Token Index: 622

Text #13

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0766. Min Act: -0.0003

Data Index: 1226851 (C4 (Web Text))

Max Activating Token Index: 642

Text #14

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0767. Min Act: -0.0003

Data Index: 1124815 (C4 (Web Text))

Max Activating Token Index: 558

Text #15

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0760. Min Act: -0.0003

Data Index: 1154716 (C4 (Web Text))

Max Activating Token Index: 282

Text #16

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0754. Min Act: -0.0003

Data Index: 886037 (C4 (Web Text))

Max Activating Token Index: 406

Text #17

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0745. Min Act: -0.0003

Data Index: 529313 (C4 (Web Text))

Max Activating Token Index: 948

Text #18

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0736. Min Act: -0.0003

Data Index: 947680 (C4 (Web Text))

Max Activating Token Index: 688

Text #19

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0708. Min Act: -0.0002

Data Index: 884537 (C4 (Web Text))

Max Activating Token Index: 149