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

Dataset: Open Web Text

Neuron 1352 in Layer 2

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: 5.1314. Min Range: -5.1314

Max Act: 5.1314. Min Act: -0.1700

Data Index: 6225006 (Open Web Text)

Max Activating Token Index: 342

Text #1

Max Range: 5.1314. Min Range: -5.1314

Max Act: 5.0766. Min Act: -0.1700

Data Index: 2526379 (Open Web Text)

Max Activating Token Index: 49

Text #2

Max Range: 5.1314. Min Range: -5.1314

Max Act: 5.0790. Min Act: -0.1700

Data Index: 480449 (Open Web Text)

Max Activating Token Index: 47

Text #3

Max Range: 5.1314. Min Range: -5.1314

Max Act: 5.0204. Min Act: -0.1700

Data Index: 1066570 (Open Web Text)

Max Activating Token Index: 515

Text #4

Max Range: 5.1314. Min Range: -5.1314

Max Act: 5.0505. Min Act: -0.1700

Data Index: 1571408 (Open Web Text)

Max Activating Token Index: 641

Text #5

Max Range: 5.1314. Min Range: -5.1314

Max Act: 5.0081. Min Act: -0.1700

Data Index: 5266410 (Open Web Text)

Max Activating Token Index: 75

Text #6

Max Range: 5.1314. Min Range: -5.1314

Max Act: 4.9735. Min Act: -0.1700

Data Index: 243203 (Open Web Text)

Max Activating Token Index: 73

Text #7

Max Range: 5.1314. Min Range: -5.1314

Max Act: 4.9712. Min Act: -0.1700

Data Index: 2942204 (Open Web Text)

Max Activating Token Index: 111

Text #8

Max Range: 5.1314. Min Range: -5.1314

Max Act: 4.9782. Min Act: -0.1700

Data Index: 6937410 (Open Web Text)

Max Activating Token Index: 475

Text #9

Max Range: 5.1314. Min Range: -5.1314

Max Act: 4.9523. Min Act: -0.1700

Data Index: 1378202 (Open Web Text)

Max Activating Token Index: 60

Text #10

Max Range: 5.1314. Min Range: -5.1314

Max Act: 4.8863. Min Act: -0.1700

Data Index: 1358790 (Open Web Text)

Max Activating Token Index: 146

Text #11

Max Range: 5.1314. Min Range: -5.1314

Max Act: 4.8945. Min Act: -0.1700

Data Index: 8639690 (Open Web Text)

Max Activating Token Index: 150

Text #12

Max Range: 5.1314. Min Range: -5.1314

Max Act: 4.9165. Min Act: -0.1700

Data Index: 7698176 (Open Web Text)

Max Activating Token Index: 431

Text #13

Max Range: 5.1314. Min Range: -5.1314

Max Act: 4.8506. Min Act: -0.1700

Data Index: 3818329 (Open Web Text)

Max Activating Token Index: 934

Text #14

Max Range: 5.1314. Min Range: -5.1314

Max Act: 4.8483. Min Act: -0.1700

Data Index: 2406822 (Open Web Text)

Max Activating Token Index: 12

Text #15

Max Range: 5.1314. Min Range: -5.1314

Max Act: 4.8191. Min Act: -0.1700

Data Index: 889654 (Open Web Text)

Max Activating Token Index: 205

Text #16

Max Range: 5.1314. Min Range: -5.1314

Max Act: 4.8168. Min Act: -0.1700

Data Index: 9972 (Open Web Text)

Max Activating Token Index: 66

Text #17

Max Range: 5.1314. Min Range: -5.1314

Max Act: 4.8470. Min Act: -0.1700

Data Index: 7780802 (Open Web Text)

Max Activating Token Index: 510

Text #18

Max Range: 5.1314. Min Range: -5.1314

Max Act: 4.8362. Min Act: -0.1700

Data Index: 6794478 (Open Web Text)

Max Activating Token Index: 28

Text #19

Max Range: 5.1314. Min Range: -5.1314

Max Act: 4.8355. Min Act: -0.1700

Data Index: 8291974 (Open Web Text)

Max Activating Token Index: 50