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

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

Neuron 2722 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4218. Min Range: -0.4218

Max Act: 0.4218. Min Act: -0.0003

Data Index: 76355 (C4 (Web Text))

Max Activating Token Index: 56

Text #1

Max Range: 0.4218. Min Range: -0.4218

Max Act: 0.4134. Min Act: -0.0003

Data Index: 1145776 (C4 (Web Text))

Max Activating Token Index: 670

Text #2

Max Range: 0.4218. Min Range: -0.4218

Max Act: 0.4207. Min Act: -0.0003

Data Index: 278837 (C4 (Web Text))

Max Activating Token Index: 946

Text #3

Max Range: 0.4218. Min Range: -0.4218

Max Act: 0.4169. Min Act: -0.0003

Data Index: 558041 (C4 (Web Text))

Max Activating Token Index: 105

Text #4

Max Range: 0.4218. Min Range: -0.4218

Max Act: 0.4083. Min Act: -0.0003

Data Index: 872065 (C4 (Web Text))

Max Activating Token Index: 456

Text #5

Max Range: 0.4218. Min Range: -0.4218

Max Act: 0.4142. Min Act: -0.0003

Data Index: 60512 (C4 (Web Text))

Max Activating Token Index: 494

Text #6

Max Range: 0.4218. Min Range: -0.4218

Max Act: 0.3991. Min Act: -0.0003

Data Index: 315560 (C4 (Web Text))

Max Activating Token Index: 432

Text #7

Max Range: 0.4218. Min Range: -0.4218

Max Act: 0.3935. Min Act: -0.0003

Data Index: 900075 (C4 (Web Text))

Max Activating Token Index: 89

Text #8

Max Range: 0.4218. Min Range: -0.4218

Max Act: 0.3920. Min Act: -0.0003

Data Index: 1277395 (C4 (Web Text))

Max Activating Token Index: 218

Text #9

Max Range: 0.4218. Min Range: -0.4218

Max Act: 0.3975. Min Act: -0.0003

Data Index: 952775 (C4 (Web Text))

Max Activating Token Index: 868

Text #10

Max Range: 0.4218. Min Range: -0.4218

Max Act: 0.3856. Min Act: -0.0003

Data Index: 842890 (C4 (Web Text))

Max Activating Token Index: 193

Text #11

Max Range: 0.4218. Min Range: -0.4218

Max Act: 0.3811. Min Act: -0.0003

Data Index: 194177 (C4 (Web Text))

Max Activating Token Index: 931

Text #12

Max Range: 0.4218. Min Range: -0.4218

Max Act: 0.3788. Min Act: -0.0003

Data Index: 1161713 (C4 (Web Text))

Max Activating Token Index: 327

Text #13

Max Range: 0.4218. Min Range: -0.4218

Max Act: 0.3800. Min Act: -0.0003

Data Index: 961421 (C4 (Web Text))

Max Activating Token Index: 971

Text #14

Max Range: 0.4218. Min Range: -0.4218

Max Act: 0.3711. Min Act: -0.0003

Data Index: 561267 (C4 (Web Text))

Max Activating Token Index: 296

Text #15

Max Range: 0.4218. Min Range: -0.4218

Max Act: 0.3586. Min Act: -0.0003

Data Index: 555548 (C4 (Web Text))

Max Activating Token Index: 869

Text #16

Max Range: 0.4218. Min Range: -0.4218

Max Act: 0.3655. Min Act: -0.0003

Data Index: 883493 (C4 (Web Text))

Max Activating Token Index: 214

Text #17

Max Range: 0.4218. Min Range: -0.4218

Max Act: 0.3822. Min Act: -0.0003

Data Index: 712906 (C4 (Web Text))

Max Activating Token Index: 366

Text #18

Max Range: 0.4218. Min Range: -0.4218

Max Act: 0.3770. Min Act: -0.0003

Data Index: 564395 (C4 (Web Text))

Max Activating Token Index: 37

Text #19

Max Range: 0.4218. Min Range: -0.4218

Max Act: 0.3593. Min Act: -0.0003

Data Index: 403855 (C4 (Web Text))

Max Activating Token Index: 248