The particular data set you need will depend highly on your choice of the kernel function, so It seems the easiest method is simply creating a toy data set yourself.

Some helpful ideas:

- Concentric circles
- Spiral-shaped classes
- Nested banana-shaped classes

If you just want a random data set that is not linearly separable, So for your query, you can use the iris data set. It is a multivariate data set where at least a couple of the classes in question are not linearly separable.

It's comprised of three classes, Class I is linearly separable from Class II and III; Class II and III are not linearly separable. If you want to use this data set, for convenience-sake you might prefer to remove Class I (approx. the first 50 data rows), so what remains is a two-class system, in which the two remaining classes are not linearly separable.

The iris data set is quite small (150 x 4, or 50 rows/class x four features)--depending on where you are with your SVM prototype testing, this might be exactly what you want, or you might want a larger data set.

If you wish to learn about Support Vector Machine then visit this Support Vector Machine Tutorial.