NLP: How to look at sentence encoding in torchtext?

TEXT = data.Field(tokenize = 'spacy',
                  tokenizer_language = 'en_core_web_sm',
                  include_lengths = True)

LABEL = data.LabelField(dtype = torch.float)

train_data, test_data = datasets.IMDB.splits(TEXT, LABEL)
train_data, valid_data = train_data.split(random_state = random.seed(SEED))

MAX_VOCAB_SIZE = 25_000

TEXT.build_vocab(train_data, 
                 max_size = MAX_VOCAB_SIZE, 
                 vectors = "glove.6B.100d", 
                 unk_init = torch.Tensor.normal_)
LABEL.build_vocab(train_data)

Suppose I have built vocabulary from training data like above. Now I want to take a look of the one-hot encoding of the sentences in the training data, how should I do that? (I know iterator will automatically give the encoded and padded sentence, but I just want to take a look of what the encoding look like).

Thanks in advance!