switching to c4

app.py

@@ -25,7 +25,7 @@ def get_dataset(name, n_items=1000):
 
 
 # names = ["oscar", "the_pile", "c4", "roots_en"]
-name = "oscar"
+name = "c4"
 df, max_perplexity = get_dataset(name)
 
 # Create scatter plot with x and y coordinates