This one is actually interesting: The statistical difference highlights that the people who eventually quit were actually better at following the scientific protocol than those who went to the end.

And also this: The most frequent violation in obedient sessions (those who shocked till the end) involved reading the memory test questions over the simulated screams of the learner. Doing this effectively guaranteed that the learner would fail the test and receive another shock.

Basically, being willing to shock other people without stopping was more about violence itself being permitted then about being obedient person. Rule followers followed the protocol until they concluded "nope, this is too much" and stopped mistreating the victim.