As a former perceptual neuroscientist, I can assure you that ML "attention" has very little to do with biological attention.
When you think about it that way, you can bridge the two types of cognition more usefully. The how of intelligence, what attention consists of, can remain completely different, while the why can feel so universal that humans can easily forget they're talking to a machine.
How attention affects biological neurons has little in common with the ML mechanism of attention.
Salience explains the "why", but I'm talking about the "how".
E.g., a high-level auditory neuron might primarily fire in response to high-pitched voices, but if you hear someone say your name in a high-pitched voice at a party, you can bias that neuron to try more selectively fire in response to just their voice, "tuning out" similarly-pitched voices.