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

Dataset: Open Web Text

Neuron 88 in Layer 0

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: 3.0463. Min Range: -3.0463

Max Act: 3.0463. Min Act: -0.1700

Data Index: 4250739 (Open Web Text)

Max Activating Token Index: 5

Text #1

Max Range: 3.0463. Min Range: -3.0463

Max Act: 3.0021. Min Act: -0.1700

Data Index: 3252560 (Open Web Text)

Max Activating Token Index: 269

Text #2

Max Range: 3.0463. Min Range: -3.0463

Max Act: 2.9201. Min Act: -0.1700

Data Index: 1976336 (Open Web Text)

Max Activating Token Index: 174

Text #3

Max Range: 3.0463. Min Range: -3.0463

Max Act: 2.9093. Min Act: -0.1700

Data Index: 1294951 (Open Web Text)

Max Activating Token Index: 5

Text #4

Max Range: 3.0463. Min Range: -3.0463

Max Act: 2.8803. Min Act: -0.1700

Data Index: 1083326 (Open Web Text)

Max Activating Token Index: 5

Text #5

Max Range: 3.0463. Min Range: -3.0463

Max Act: 2.8651. Min Act: -0.1700

Data Index: 7691744 (Open Web Text)

Max Activating Token Index: 16

Text #6

Max Range: 3.0463. Min Range: -3.0463

Max Act: 2.8707. Min Act: -0.1700

Data Index: 7650930 (Open Web Text)

Max Activating Token Index: 4

Text #7

Max Range: 3.0463. Min Range: -3.0463

Max Act: 2.8641. Min Act: -0.1700

Data Index: 4080235 (Open Web Text)

Max Activating Token Index: 5

Text #8

Max Range: 3.0463. Min Range: -3.0463

Max Act: 2.8520. Min Act: -0.1700

Data Index: 874525 (Open Web Text)

Max Activating Token Index: 5

Text #9

Max Range: 3.0463. Min Range: -3.0463

Max Act: 2.8568. Min Act: -0.1700

Data Index: 2116604 (Open Web Text)

Max Activating Token Index: 5

Text #10

Max Range: 3.0463. Min Range: -3.0463

Max Act: 2.8557. Min Act: -0.1700

Data Index: 5481012 (Open Web Text)

Max Activating Token Index: 6

Text #11

Max Range: 3.0463. Min Range: -3.0463

Max Act: 2.8610. Min Act: -0.1700

Data Index: 7811714 (Open Web Text)

Max Activating Token Index: 162

Text #12

Max Range: 3.0463. Min Range: -3.0463

Max Act: 2.8345. Min Act: -0.1700

Data Index: 2262650 (Open Web Text)

Max Activating Token Index: 3

Text #13

Max Range: 3.0463. Min Range: -3.0463

Max Act: 2.8335. Min Act: -0.1700

Data Index: 5758873 (Open Web Text)

Max Activating Token Index: 17

Text #14

Max Range: 3.0463. Min Range: -3.0463

Max Act: 2.8490. Min Act: -0.1700

Data Index: 5364106 (Open Web Text)

Max Activating Token Index: 8

Text #15

Max Range: 3.0463. Min Range: -3.0463

Max Act: 2.8472. Min Act: -0.1700

Data Index: 4371205 (Open Web Text)

Max Activating Token Index: 10

Text #16

Max Range: 3.0463. Min Range: -3.0463

Max Act: 2.8221. Min Act: -0.1700

Data Index: 2392172 (Open Web Text)

Max Activating Token Index: 224

Text #17

Max Range: 3.0463. Min Range: -3.0463

Max Act: 2.8273. Min Act: -0.1700

Data Index: 5517933 (Open Web Text)

Max Activating Token Index: 106

Text #18

Max Range: 3.0463. Min Range: -3.0463

Max Act: 2.8073. Min Act: -0.1700

Data Index: 1912038 (Open Web Text)

Max Activating Token Index: 6

Text #19

Max Range: 3.0463. Min Range: -3.0463

Max Act: 2.8080. Min Act: -0.1700

Data Index: 1681035 (Open Web Text)

Max Activating Token Index: 7