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

Dataset: Open Web Text

Neuron 1868 in Layer 3

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: 3.8287. Min Range: -3.8287

Max Act: 3.8287. Min Act: -0.1700

Data Index: 1591901 (Open Web Text)

Max Activating Token Index: 456

Text #1

Max Range: 3.8287. Min Range: -3.8287

Max Act: 3.7301. Min Act: -0.1700

Data Index: 6427762 (Open Web Text)

Max Activating Token Index: 384

Text #2

Max Range: 3.8287. Min Range: -3.8287

Max Act: 3.6876. Min Act: -0.1700

Data Index: 2086113 (Open Web Text)

Max Activating Token Index: 4

Text #3

Max Range: 3.8287. Min Range: -3.8287

Max Act: 3.6681. Min Act: -0.1700

Data Index: 6166442 (Open Web Text)

Max Activating Token Index: 21

Text #4

Max Range: 3.8287. Min Range: -3.8287

Max Act: 3.6621. Min Act: -0.1700

Data Index: 6987181 (Open Web Text)

Max Activating Token Index: 542

Text #5

Max Range: 3.8287. Min Range: -3.8287

Max Act: 3.6446. Min Act: -0.1700

Data Index: 8286160 (Open Web Text)

Max Activating Token Index: 13

Text #6

Max Range: 3.8287. Min Range: -3.8287

Max Act: 3.5801. Min Act: -0.1700

Data Index: 3310941 (Open Web Text)

Max Activating Token Index: 836

Text #7

Max Range: 3.8287. Min Range: -3.8287

Max Act: 3.5539. Min Act: -0.1700

Data Index: 8658295 (Open Web Text)

Max Activating Token Index: 360

Text #8

Max Range: 3.8287. Min Range: -3.8287

Max Act: 3.5369. Min Act: -0.1700

Data Index: 6660894 (Open Web Text)

Max Activating Token Index: 870

Text #9

Max Range: 3.8287. Min Range: -3.8287

Max Act: 3.5383. Min Act: -0.1700

Data Index: 6316332 (Open Web Text)

Max Activating Token Index: 761

Text #10

Max Range: 3.8287. Min Range: -3.8287

Max Act: 3.4862. Min Act: -0.1700

Data Index: 2354807 (Open Web Text)

Max Activating Token Index: 753

Text #11

Max Range: 3.8287. Min Range: -3.8287

Max Act: 3.5170. Min Act: -0.1700

Data Index: 8558475 (Open Web Text)

Max Activating Token Index: 160

Text #12

Max Range: 3.8287. Min Range: -3.8287

Max Act: 3.5634. Min Act: -0.1700

Data Index: 6429939 (Open Web Text)

Max Activating Token Index: 5

Text #13

Max Range: 3.8287. Min Range: -3.8287

Max Act: 3.5811. Min Act: -0.1700

Data Index: 7870391 (Open Web Text)

Max Activating Token Index: 771

Text #14

Max Range: 3.8287. Min Range: -3.8287

Max Act: 3.5123. Min Act: -0.1700

Data Index: 7526982 (Open Web Text)

Max Activating Token Index: 281

Text #15

Max Range: 3.8287. Min Range: -3.8287

Max Act: 3.5021. Min Act: -0.1700

Data Index: 6222720 (Open Web Text)

Max Activating Token Index: 380

Text #16

Max Range: 3.8287. Min Range: -3.8287

Max Act: 3.4600. Min Act: -0.1700

Data Index: 1129690 (Open Web Text)

Max Activating Token Index: 767

Text #17

Max Range: 3.8287. Min Range: -3.8287

Max Act: 3.4930. Min Act: -0.1700

Data Index: 5690730 (Open Web Text)

Max Activating Token Index: 309

Text #18

Max Range: 3.8287. Min Range: -3.8287

Max Act: 3.5130. Min Act: -0.1700

Data Index: 2093853 (Open Web Text)

Max Activating Token Index: 318

Text #19

Max Range: 3.8287. Min Range: -3.8287

Max Act: 3.5166. Min Act: -0.1700

Data Index: 3615724 (Open Web Text)

Max Activating Token Index: 32