A new approach to computer modelling of neuronal stochastic activity is described. The output dynamic activity which depends on the types and the number of input synapses, weights of the synaptic efficacy, the absolute refractory phase duration and threshold level is evaluated on this model in some types of Gaussian input processes. The behaviour of this model for one excitatory and one inhibitory synapse is described in dependence on the changes of excitation weight. The neuronal behaviour presented depends on the number of interspike intervals and the excitation weight and interspike interval density distribution. A novel concept of the e-curve is being introduced, which shows the dependence of the number of output interspike intervals on the weight of excitation on a stable inhibition level, the absolute refractory phase value and the threshold level. The properties of e-curves are discussed. Furthermore, examples of transformations of input stochastic processes are mentioned from the aspect of density distribution changes of interspike intervals.