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

Dataset: Open Web Text

Neuron 706 in Layer 15

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.1109. Min Range: -4.1109

Max Act: 4.1109. Min Act: -0.1700

Data Index: 7548260 (Open Web Text)

Max Activating Token Index: 505

Text #1

Max Range: 4.1109. Min Range: -4.1109

Max Act: 4.1109. Min Act: -0.1700

Data Index: 5773095 (Open Web Text)

Max Activating Token Index: 443

Text #2

Max Range: 4.1109. Min Range: -4.1109

Max Act: 4.0484. Min Act: -0.1700

Data Index: 3377468 (Open Web Text)

Max Activating Token Index: 414

Text #3

Max Range: 4.1109. Min Range: -4.1109

Max Act: 4.0484. Min Act: -0.1700

Data Index: 5701980 (Open Web Text)

Max Activating Token Index: 856

Text #4

Max Range: 4.1109. Min Range: -4.1109

Max Act: 4.0484. Min Act: -0.1700

Data Index: 7664116 (Open Web Text)

Max Activating Token Index: 574

Text #5

Max Range: 4.1109. Min Range: -4.1109

Max Act: 4.0484. Min Act: -0.1700

Data Index: 3336709 (Open Web Text)

Max Activating Token Index: 351

Text #6

Max Range: 4.1109. Min Range: -4.1109

Max Act: 4.0172. Min Act: -0.1700

Data Index: 504777 (Open Web Text)

Max Activating Token Index: 950

Text #7

Max Range: 4.1109. Min Range: -4.1109

Max Act: 4.0172. Min Act: -0.1700

Data Index: 2522364 (Open Web Text)

Max Activating Token Index: 307

Text #8

Max Range: 4.1109. Min Range: -4.1109

Max Act: 3.9859. Min Act: -0.1700

Data Index: 7590018 (Open Web Text)

Max Activating Token Index: 857

Text #9

Max Range: 4.1109. Min Range: -4.1109

Max Act: 4.0172. Min Act: -0.1700

Data Index: 4141232 (Open Web Text)

Max Activating Token Index: 1000

Text #10

Max Range: 4.1109. Min Range: -4.1109

Max Act: 4.0172. Min Act: -0.1700

Data Index: 8461195 (Open Web Text)

Max Activating Token Index: 563

Text #11

Max Range: 4.1109. Min Range: -4.1109

Max Act: 3.9546. Min Act: -0.1700

Data Index: 2522367 (Open Web Text)

Max Activating Token Index: 231

Text #12

Max Range: 4.1109. Min Range: -4.1109

Max Act: 3.9859. Min Act: -0.1700

Data Index: 2255354 (Open Web Text)

Max Activating Token Index: 64

Text #13

Max Range: 4.1109. Min Range: -4.1109

Max Act: 3.9546. Min Act: -0.1700

Data Index: 5288089 (Open Web Text)

Max Activating Token Index: 279

Text #14

Max Range: 4.1109. Min Range: -4.1109

Max Act: 3.9859. Min Act: -0.1700

Data Index: 2522362 (Open Web Text)

Max Activating Token Index: 592

Text #15

Max Range: 4.1109. Min Range: -4.1109

Max Act: 3.9859. Min Act: -0.1700

Data Index: 7667666 (Open Web Text)

Max Activating Token Index: 459

Text #16

Max Range: 4.1109. Min Range: -4.1109

Max Act: 3.9859. Min Act: -0.1700

Data Index: 7873086 (Open Web Text)

Max Activating Token Index: 120

Text #17

Max Range: 4.1109. Min Range: -4.1109

Max Act: 4.0172. Min Act: -0.1700

Data Index: 1760582 (Open Web Text)

Max Activating Token Index: 513

Text #18

Max Range: 4.1109. Min Range: -4.1109

Max Act: 4.0172. Min Act: -0.1700

Data Index: 646450 (Open Web Text)

Max Activating Token Index: 606

Text #19

Max Range: 4.1109. Min Range: -4.1109

Max Act: 3.9859. Min Act: -0.1700

Data Index: 2522368 (Open Web Text)

Max Activating Token Index: 505