While many studies have shown that linguistic information is encoded in hidden word representations, few have studied individual neurons, to show how and in which neurons it is encoded. Among these, the common approach is to use an external probe to rank neurons according to their relevance to some linguistic attribute, and to evaluate the obtained ranking using the same probe that produced it. We show two pitfalls in this methodology: 1. It confounds distinct factors: probe quality and ranking quality. We separate them and draw conclusions on each. 2. It focuses on encoded information, rather than information that is used by the model. We show that these are not the same. We compare two recent ranking methods and a simple one we introduce, and evaluate them with regard to both of these aspects.

翻译：虽然许多研究表明语言信息以隐藏的字表形式编码,但很少有人研究单个神经元,以显示其是如何和在哪些方面编码的。其中,共同的方法是使用外部探测器根据神经元与某些语言属性的相关性对其进行排序,并使用生成该神经元的同一探测器对所获得的排名进行评估。我们在这种方法中发现了两个缺陷:1.它混淆了不同的因素:检查质量和排序质量,我们将它们分开,就每个要素作出结论。2.它侧重于编码信息,而不是模型使用的信息。我们表明,这些方法并不一样。我们比较了最近采用的两种排序方法和我们采用的简单方法,并对这两个方面进行了评估。