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

Dataset: Open Web Text

Neuron 3344 in Layer 28

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.1109. Min Range: -5.1109

Max Act: 5.1109. Min Act: -0.1700

Data Index: 4940148 (Open Web Text)

Max Activating Token Index: 957

Text #1

Max Range: 5.1109. Min Range: -5.1109

Max Act: 5.0172. Min Act: -0.1700

Data Index: 8005437 (Open Web Text)

Max Activating Token Index: 190

Text #2

Max Range: 5.1109. Min Range: -5.1109

Max Act: 4.9547. Min Act: -0.1700

Data Index: 8078260 (Open Web Text)

Max Activating Token Index: 162

Text #3

Max Range: 5.1109. Min Range: -5.1109

Max Act: 4.9234. Min Act: -0.1700

Data Index: 8390239 (Open Web Text)

Max Activating Token Index: 288

Text #4

Max Range: 5.1109. Min Range: -5.1109

Max Act: 4.8922. Min Act: -0.1700

Data Index: 2958567 (Open Web Text)

Max Activating Token Index: 561

Text #5

Max Range: 5.1109. Min Range: -5.1109

Max Act: 4.8609. Min Act: -0.1700

Data Index: 5467894 (Open Web Text)

Max Activating Token Index: 569

Text #6

Max Range: 5.1109. Min Range: -5.1109

Max Act: 4.8609. Min Act: -0.1700

Data Index: 6106576 (Open Web Text)

Max Activating Token Index: 824

Text #7

Max Range: 5.1109. Min Range: -5.1109

Max Act: 4.8297. Min Act: -0.1700

Data Index: 5089637 (Open Web Text)

Max Activating Token Index: 377

Text #8

Max Range: 5.1109. Min Range: -5.1109

Max Act: 4.8297. Min Act: -0.1700

Data Index: 3275857 (Open Web Text)

Max Activating Token Index: 229

Text #9

Max Range: 5.1109. Min Range: -5.1109

Max Act: 4.8297. Min Act: -0.1700

Data Index: 7673106 (Open Web Text)

Max Activating Token Index: 446

Text #10

Max Range: 5.1109. Min Range: -5.1109

Max Act: 4.7984. Min Act: -0.1700

Data Index: 6969057 (Open Web Text)

Max Activating Token Index: 564

Text #11

Max Range: 5.1109. Min Range: -5.1109

Max Act: 4.7672. Min Act: -0.1700

Data Index: 1575637 (Open Web Text)

Max Activating Token Index: 854

Text #12

Max Range: 5.1109. Min Range: -5.1109

Max Act: 4.7672. Min Act: -0.1700

Data Index: 1744011 (Open Web Text)

Max Activating Token Index: 315

Text #13

Max Range: 5.1109. Min Range: -5.1109

Max Act: 4.7359. Min Act: -0.1700

Data Index: 298077 (Open Web Text)

Max Activating Token Index: 320

Text #14

Max Range: 5.1109. Min Range: -5.1109

Max Act: 4.7359. Min Act: -0.1700

Data Index: 5009780 (Open Web Text)

Max Activating Token Index: 735

Text #15

Max Range: 5.1109. Min Range: -5.1109

Max Act: 4.7359. Min Act: -0.1700

Data Index: 6444531 (Open Web Text)

Max Activating Token Index: 948

Text #16

Max Range: 5.1109. Min Range: -5.1109

Max Act: 4.7359. Min Act: -0.1700

Data Index: 2592524 (Open Web Text)

Max Activating Token Index: 235

Text #17

Max Range: 5.1109. Min Range: -5.1109

Max Act: 4.7359. Min Act: -0.1700

Data Index: 7046448 (Open Web Text)

Max Activating Token Index: 649

Text #18

Max Range: 5.1109. Min Range: -5.1109

Max Act: 4.6734. Min Act: -0.1700

Data Index: 4541620 (Open Web Text)

Max Activating Token Index: 711

Text #19

Max Range: 5.1109. Min Range: -5.1109

Max Act: 4.7047. Min Act: -0.1700

Data Index: 3050561 (Open Web Text)

Max Activating Token Index: 229