Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer

Dataset: Open Web Text

Neuron 2962 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')

Text #0

Max Range: 6.1109. Min Range: -6.1109

Max Act: 6.1109. Min Act: -0.1700

Data Index: 8206410 (Open Web Text)

Max Activating Token Index: 579

Text #1

Max Range: 6.1109. Min Range: -6.1109

Max Act: 6.1109. Min Act: -0.1700

Data Index: 8777447 (Open Web Text)

Max Activating Token Index: 492

Text #2

Max Range: 6.1109. Min Range: -6.1109

Max Act: 5.9234. Min Act: -0.1700

Data Index: 6479327 (Open Web Text)

Max Activating Token Index: 37

Text #3

Max Range: 6.1109. Min Range: -6.1109

Max Act: 5.8921. Min Act: -0.1700

Data Index: 7447746 (Open Web Text)

Max Activating Token Index: 564

Text #4

Max Range: 6.1109. Min Range: -6.1109

Max Act: 5.8609. Min Act: -0.1700

Data Index: 3204690 (Open Web Text)

Max Activating Token Index: 498

Text #5

Max Range: 6.1109. Min Range: -6.1109

Max Act: 5.8296. Min Act: -0.1700

Data Index: 8275719 (Open Web Text)

Max Activating Token Index: 682

Text #6

Max Range: 6.1109. Min Range: -6.1109

Max Act: 5.7984. Min Act: -0.1700

Data Index: 1782903 (Open Web Text)

Max Activating Token Index: 502

Text #7

Max Range: 6.1109. Min Range: -6.1109

Max Act: 5.7984. Min Act: -0.1700

Data Index: 5410715 (Open Web Text)

Max Activating Token Index: 349

Text #8

Max Range: 6.1109. Min Range: -6.1109

Max Act: 5.7984. Min Act: -0.1700

Data Index: 375759 (Open Web Text)

Max Activating Token Index: 84

Text #9

Max Range: 6.1109. Min Range: -6.1109

Max Act: 5.7984. Min Act: -0.1700

Data Index: 6681811 (Open Web Text)

Max Activating Token Index: 824

Text #10

Max Range: 6.1109. Min Range: -6.1109

Max Act: 5.8296. Min Act: -0.1700

Data Index: 8797120 (Open Web Text)

Max Activating Token Index: 77

Text #11

Max Range: 6.1109. Min Range: -6.1109

Max Act: 5.7984. Min Act: -0.1700

Data Index: 186799 (Open Web Text)

Max Activating Token Index: 656

Text #12

Max Range: 6.1109. Min Range: -6.1109

Max Act: 5.7671. Min Act: -0.1700

Data Index: 4828653 (Open Web Text)

Max Activating Token Index: 47

Text #13

Max Range: 6.1109. Min Range: -6.1109

Max Act: 5.7984. Min Act: -0.1700

Data Index: 1566641 (Open Web Text)

Max Activating Token Index: 146

Text #14

Max Range: 6.1109. Min Range: -6.1109

Max Act: 5.7671. Min Act: -0.1700

Data Index: 3820387 (Open Web Text)

Max Activating Token Index: 382

Text #15

Max Range: 6.1109. Min Range: -6.1109

Max Act: 5.7671. Min Act: -0.1700

Data Index: 4570825 (Open Web Text)

Max Activating Token Index: 645

Text #16

Max Range: 6.1109. Min Range: -6.1109

Max Act: 5.7671. Min Act: -0.1700

Data Index: 26951 (Open Web Text)

Max Activating Token Index: 623

Text #17

Max Range: 6.1109. Min Range: -6.1109

Max Act: 5.7359. Min Act: -0.1700

Data Index: 4068338 (Open Web Text)

Max Activating Token Index: 300

Text #18

Max Range: 6.1109. Min Range: -6.1109

Max Act: 5.7359. Min Act: -0.1700

Data Index: 5771524 (Open Web Text)

Max Activating Token Index: 515

Text #19

Max Range: 6.1109. Min Range: -6.1109

Max Act: 5.7359. Min Act: -0.1700

Data Index: 5881395 (Open Web Text)

Max Activating Token Index: 357