An experiment is a recorder + inputs + probes, saved as a self-contained .nsz artifact. This walkthrough records 64 inputs against a small transformer and reloads them in a fresh interpreter.
1. Set up the recorder
first_experiment.py··python
import neuronscope as ns
from transformers import AutoModel
model = AutoModel.from_pretrained("distilbert-base-uncased")
ds = ns.datasets.tiny_imdb(n=64)
probes = [ns.probes.Activations("transformer.layer.*.output")]2. Run and save
first_experiment.py··python
with ns.Recorder(model, probes=probes) as rec:
rec.record(ds)
rec.save("first.nsz")3. Reload and inspect
shellfocus a line, then ⌘/Ctrl+C or Enterbash
ns show first.nszns show first.nsz --layer transformer.layer.0.output4. Verify round-trip
Reload in Python and check tensor equality against a re-record on the same seed.
verify.py··python
import neuronscope as ns, torch
a = ns.load("first.nsz")
b = ns.load("first.nsz") # or re-record with the same seed
for layer in a.layers():
assert torch.equal(a[layer], b[layer])- Artifacts embed the environment fingerprint — a mismatch will refuse to compare.
- Recorded tensors are stored in native dtype; reloads do not cast.