Data Clustering stands for a group of methods classifying patterns into groups and retrieving similarities or dissimilarities of a collection of objects. Clustering is used for pattern recognition, machine learning, etc. One of the approaches to clustering is optimization. The aim of the optimization is finding the best solution in the search space of a problem as much as possible. Many optimization methods were modified to solve clustering problems in literature. Gray Wolf Optimizer (GWO) is one of the nature-inspired meta-heuristic algorithms simulating the hunting of gray wolves. GWO has applied to solve several optimization issues in different fields. In this study, GWO was examined in the case of data clustering. GWO was modified to get better clustering results and applied to well-known benchmark data sets. The performance of GWO was compared to the other algorithms used as clustering. The results show that GWO can be used for data clustering successfully.