Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer

Dataset: Open Web Text

Neuron 1917 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gpt2-small')

Click the toggle to see the full text!

Text #0

Max Range: 3.1412. Min Range: -3.1412

Max Act: 3.1412. Min Act: -0.1700

Data Index: 5167644 (Open Web Text)

Max Activating Token Index: 962

Text #1

Max Range: 3.1412. Min Range: -3.1412

Max Act: 3.1096. Min Act: -0.1700

Data Index: 4457657 (Open Web Text)

Max Activating Token Index: 962

Text #2

Max Range: 3.1412. Min Range: -3.1412

Max Act: 3.1282. Min Act: -0.1700

Data Index: 8469575 (Open Web Text)

Max Activating Token Index: 62

Text #3

Max Range: 3.1412. Min Range: -3.1412

Max Act: 3.0997. Min Act: -0.1700

Data Index: 7158695 (Open Web Text)

Max Activating Token Index: 945

Text #4

Max Range: 3.1412. Min Range: -3.1412

Max Act: 3.0549. Min Act: -0.1700

Data Index: 216149 (Open Web Text)

Max Activating Token Index: 589

Text #5

Max Range: 3.1412. Min Range: -3.1412

Max Act: 3.0522. Min Act: -0.1700

Data Index: 5946908 (Open Web Text)

Max Activating Token Index: 977

Text #6

Max Range: 3.1412. Min Range: -3.1412

Max Act: 2.9916. Min Act: -0.1700

Data Index: 6736764 (Open Web Text)

Max Activating Token Index: 717

Text #7

Max Range: 3.1412. Min Range: -3.1412

Max Act: 2.9551. Min Act: -0.1700

Data Index: 6761559 (Open Web Text)

Max Activating Token Index: 804

Text #8

Max Range: 3.1412. Min Range: -3.1412

Max Act: 2.9619. Min Act: -0.1700

Data Index: 4256160 (Open Web Text)

Max Activating Token Index: 1003

Text #9

Max Range: 3.1412. Min Range: -3.1412

Max Act: 2.9167. Min Act: -0.1700

Data Index: 3376948 (Open Web Text)

Max Activating Token Index: 261

Text #10

Max Range: 3.1412. Min Range: -3.1412

Max Act: 2.9117. Min Act: -0.1700

Data Index: 1040733 (Open Web Text)

Max Activating Token Index: 824

Text #11

Max Range: 3.1412. Min Range: -3.1412

Max Act: 2.9073. Min Act: -0.1700

Data Index: 559058 (Open Web Text)

Max Activating Token Index: 406

Text #12

Max Range: 3.1412. Min Range: -3.1412

Max Act: 2.8790. Min Act: -0.1700

Data Index: 6117781 (Open Web Text)

Max Activating Token Index: 873

Text #13

Max Range: 3.1412. Min Range: -3.1412

Max Act: 2.9217. Min Act: -0.1700

Data Index: 7733413 (Open Web Text)

Max Activating Token Index: 206

Text #14

Max Range: 3.1412. Min Range: -3.1412

Max Act: 2.9304. Min Act: -0.1700

Data Index: 5973754 (Open Web Text)

Max Activating Token Index: 848

Text #15

Max Range: 3.1412. Min Range: -3.1412

Max Act: 2.8993. Min Act: -0.1700

Data Index: 1586404 (Open Web Text)

Max Activating Token Index: 63

Text #16

Max Range: 3.1412. Min Range: -3.1412

Max Act: 2.8809. Min Act: -0.1700

Data Index: 1335975 (Open Web Text)

Max Activating Token Index: 936

Text #17

Max Range: 3.1412. Min Range: -3.1412

Max Act: 2.8943. Min Act: -0.1700

Data Index: 7580407 (Open Web Text)

Max Activating Token Index: 394

Text #18

Max Range: 3.1412. Min Range: -3.1412

Max Act: 2.8987. Min Act: -0.1700

Data Index: 3682644 (Open Web Text)

Max Activating Token Index: 543

Text #19

Max Range: 3.1412. Min Range: -3.1412

Max Act: 2.8504. Min Act: -0.1700

Data Index: 4614979 (Open Web Text)

Max Activating Token Index: 570