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

Dataset: Open Web Text

Neuron 3210 in Layer 31

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.1109. Min Range: -7.1109

Max Act: 7.1109. Min Act: -0.1700

Data Index: 7487702 (Open Web Text)

Max Activating Token Index: 34

Text #1

Max Range: 7.1109. Min Range: -7.1109

Max Act: 6.7359. Min Act: -0.1700

Data Index: 2856221 (Open Web Text)

Max Activating Token Index: 299

Text #2

Max Range: 7.1109. Min Range: -7.1109

Max Act: 6.7359. Min Act: -0.1700

Data Index: 330842 (Open Web Text)

Max Activating Token Index: 661

Text #3

Max Range: 7.1109. Min Range: -7.1109

Max Act: 6.7047. Min Act: -0.1700

Data Index: 2856219 (Open Web Text)

Max Activating Token Index: 235

Text #4

Max Range: 7.1109. Min Range: -7.1109

Max Act: 6.7047. Min Act: -0.1700

Data Index: 330844 (Open Web Text)

Max Activating Token Index: 725

Text #5

Max Range: 7.1109. Min Range: -7.1109

Max Act: 6.6109. Min Act: -0.1700

Data Index: 3196012 (Open Web Text)

Max Activating Token Index: 555

Text #6

Max Range: 7.1109. Min Range: -7.1109

Max Act: 6.5484. Min Act: -0.1700

Data Index: 7390065 (Open Web Text)

Max Activating Token Index: 423

Text #7

Max Range: 7.1109. Min Range: -7.1109

Max Act: 6.5797. Min Act: -0.1700

Data Index: 6902016 (Open Web Text)

Max Activating Token Index: 207

Text #8

Max Range: 7.1109. Min Range: -7.1109

Max Act: 6.4859. Min Act: -0.1700

Data Index: 2885722 (Open Web Text)

Max Activating Token Index: 849

Text #9

Max Range: 7.1109. Min Range: -7.1109

Max Act: 6.4234. Min Act: -0.1699

Data Index: 4361948 (Open Web Text)

Max Activating Token Index: 820

Text #10

Max Range: 7.1109. Min Range: -7.1109

Max Act: 6.3922. Min Act: -0.1700

Data Index: 330841 (Open Web Text)

Max Activating Token Index: 517

Text #11

Max Range: 7.1109. Min Range: -7.1109

Max Act: 6.3922. Min Act: -0.1700

Data Index: 2440850 (Open Web Text)

Max Activating Token Index: 101

Text #12

Max Range: 7.1109. Min Range: -7.1109

Max Act: 6.3922. Min Act: -0.1700

Data Index: 330843 (Open Web Text)

Max Activating Token Index: 581

Text #13

Max Range: 7.1109. Min Range: -7.1109

Max Act: 6.3609. Min Act: -0.1700

Data Index: 3195136 (Open Web Text)

Max Activating Token Index: 575

Text #14

Max Range: 7.1109. Min Range: -7.1109

Max Act: 6.3609. Min Act: -0.1700

Data Index: 558388 (Open Web Text)

Max Activating Token Index: 467

Text #15

Max Range: 7.1109. Min Range: -7.1109

Max Act: 6.3297. Min Act: -0.1700

Data Index: 2471597 (Open Web Text)

Max Activating Token Index: 381

Text #16

Max Range: 7.1109. Min Range: -7.1109

Max Act: 6.2672. Min Act: -0.1700

Data Index: 7433372 (Open Web Text)

Max Activating Token Index: 976

Text #17

Max Range: 7.1109. Min Range: -7.1109

Max Act: 6.2359. Min Act: -0.1700

Data Index: 1599190 (Open Web Text)

Max Activating Token Index: 891

Text #18

Max Range: 7.1109. Min Range: -7.1109

Max Act: 6.2047. Min Act: -0.1700

Data Index: 4833787 (Open Web Text)

Max Activating Token Index: 470

Text #19

Max Range: 7.1109. Min Range: -7.1109

Max Act: 6.2359. Min Act: -0.1700

Data Index: 3663115 (Open Web Text)

Max Activating Token Index: 885