GPUArrays `rand` seeding fails when container is bigger than workgroup size

See linked comment below for context, but in short I'm getting different results than CI on the `rand` doctest that uses `GPUArrays.default_rng(MtlArray)`

> I was just getting different results locally and figured if it's unstable between devices maybe better to filter it out but maybe we should look into that instead (in a future pr). Lmk if I should revert the regex filter.

_Originally posted by @christiangnrd in https://github.com/JuliaGPU/Metal.jl/pull/641#discussion_r2240216770_

Start with the rand doctest using GPUArrays.default_rng(MtlArray), then read the linked discussion in Metal.jl pull request 641 for the existing context. Reproduce the differing results with a container larger than the workgroup size and establish whether the doctest becomes consistent across the affected devices.

Written by the indexing model from the issue text.