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

Dataset: Open Web Text

Neuron 573 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: 3.7589. Min Range: -3.7589

Max Act: 3.7589. Min Act: -0.1700

Data Index: 3962577 (Open Web Text)

Max Activating Token Index: 451

Text #1

Max Range: 3.7589. Min Range: -3.7589

Max Act: 3.1259. Min Act: -0.1700

Data Index: 9732 (Open Web Text)

Max Activating Token Index: 260

Text #2

Max Range: 3.7589. Min Range: -3.7589

Max Act: 3.1387. Min Act: -0.1700

Data Index: 4470374 (Open Web Text)

Max Activating Token Index: 281

Text #3

Max Range: 3.7589. Min Range: -3.7589

Max Act: 3.1079. Min Act: -0.1700

Data Index: 32384 (Open Web Text)

Max Activating Token Index: 361

Text #4

Max Range: 3.7589. Min Range: -3.7589

Max Act: 3.0758. Min Act: -0.1700

Data Index: 4087936 (Open Web Text)

Max Activating Token Index: 662

Text #5

Max Range: 3.7589. Min Range: -3.7589

Max Act: 3.1160. Min Act: -0.1700

Data Index: 7619616 (Open Web Text)

Max Activating Token Index: 660

Text #6

Max Range: 3.7589. Min Range: -3.7589

Max Act: 3.0189. Min Act: -0.1700

Data Index: 1884330 (Open Web Text)

Max Activating Token Index: 565

Text #7

Max Range: 3.7589. Min Range: -3.7589

Max Act: 3.0159. Min Act: -0.1700

Data Index: 5046868 (Open Web Text)

Max Activating Token Index: 784

Text #8

Max Range: 3.7589. Min Range: -3.7589

Max Act: 2.9637. Min Act: -0.1700

Data Index: 13083 (Open Web Text)

Max Activating Token Index: 437

Text #9

Max Range: 3.7589. Min Range: -3.7589

Max Act: 2.9323. Min Act: -0.1700

Data Index: 2844588 (Open Web Text)

Max Activating Token Index: 620

Text #10

Max Range: 3.7589. Min Range: -3.7589

Max Act: 2.9912. Min Act: -0.1700

Data Index: 5233962 (Open Web Text)

Max Activating Token Index: 135

Text #11

Max Range: 3.7589. Min Range: -3.7589

Max Act: 2.9717. Min Act: -0.1700

Data Index: 8222608 (Open Web Text)

Max Activating Token Index: 557

Text #12

Max Range: 3.7589. Min Range: -3.7589

Max Act: 2.9650. Min Act: -0.1700

Data Index: 7541643 (Open Web Text)

Max Activating Token Index: 278

Text #13

Max Range: 3.7589. Min Range: -3.7589

Max Act: 2.9634. Min Act: -0.1700

Data Index: 5167677 (Open Web Text)

Max Activating Token Index: 165

Text #14

Max Range: 3.7589. Min Range: -3.7589

Max Act: 2.9412. Min Act: -0.1700

Data Index: 8734256 (Open Web Text)

Max Activating Token Index: 673

Text #15

Max Range: 3.7589. Min Range: -3.7589

Max Act: 3.0119. Min Act: -0.1700

Data Index: 2960322 (Open Web Text)

Max Activating Token Index: 447

Text #16

Max Range: 3.7589. Min Range: -3.7589

Max Act: 2.9735. Min Act: -0.1700

Data Index: 4325411 (Open Web Text)

Max Activating Token Index: 1012

Text #17

Max Range: 3.7589. Min Range: -3.7589

Max Act: 2.9966. Min Act: -0.1700

Data Index: 2076895 (Open Web Text)

Max Activating Token Index: 392

Text #18

Max Range: 3.7589. Min Range: -3.7589

Max Act: 2.9080. Min Act: -0.1700

Data Index: 1970270 (Open Web Text)

Max Activating Token Index: 370

Text #19

Max Range: 3.7589. Min Range: -3.7589

Max Act: 2.9242. Min Act: -0.1700

Data Index: 5232096 (Open Web Text)

Max Activating Token Index: 620