The full Table 1 in Investigation of stellar magnetic activity using variational autoencoder based on low-resolution spectroscopic survey (Xiang, Gu & Cao, 2022, MNRAS, 514, 4781; arXiv:2206.07257). The columns are LAMOST obsid, K2 ID, Teff, logg, [Fe/H], EW_res_Halpha, EW_res_Ca II 8498, EW_res_Ca II 8542, EW_res_Ca II 8662, log F_Halpha, log F_Ca, log R'_Halpha, log R'_Ca. The chromospheric emissions were detected and measured with the spectral subtraction technique, which removes the inactive template spectra (photospheric contribution) from the observed stellar spectra. In this work, we used the variational autoencoder neural networks to efficiently generate the proper template spectra in a data-driven manner. More details can be found in the associated paper (https://arxiv.org/abs/2206.07257). The demo code can be found on GitHub (https://github.com/xylib/vae-for-spectroscopic-survey).