Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2767 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 18.6590. Min Range: -18.6590
Max Act: 18.6590. Min Act: -0.1700
Data Index: 4606467 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 18.6590. Min Range: -18.6590
Max Act: 18.6590. Min Act: -0.1700
Data Index: 4606465 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 18.6590. Min Range: -18.6590
Max Act: 17.6590. Min Act: -0.1700
Data Index: 1693865 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 18.6590. Min Range: -18.6590
Max Act: 17.6590. Min Act: -0.1700
Data Index: 4606458 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 18.6590. Min Range: -18.6590
Max Act: 17.6590. Min Act: -0.1700
Data Index: 5971903 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 18.6590. Min Range: -18.6590
Max Act: 17.4090. Min Act: -0.1700
Data Index: 4808477 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 18.6590. Min Range: -18.6590
Max Act: 17.1590. Min Act: -0.1700
Data Index: 8493510 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 18.6590. Min Range: -18.6590
Max Act: 17.2840. Min Act: -0.1700
Data Index: 8832355 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 18.6590. Min Range: -18.6590
Max Act: 16.9090. Min Act: -0.1700
Data Index: 8117270 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 18.6590. Min Range: -18.6590
Max Act: 16.9090. Min Act: -0.1700
Data Index: 4022374 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 18.6590. Min Range: -18.6590
Max Act: 16.7840. Min Act: -0.1700
Data Index: 4606464 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 18.6590. Min Range: -18.6590
Max Act: 16.7840. Min Act: -0.1700
Data Index: 5507941 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 18.6590. Min Range: -18.6590
Max Act: 16.7840. Min Act: -0.1700
Data Index: 2974832 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 18.6590. Min Range: -18.6590
Max Act: 16.7840. Min Act: -0.1700
Data Index: 3306816 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 18.6590. Min Range: -18.6590
Max Act: 16.6590. Min Act: -0.1700
Data Index: 4996367 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 18.6590. Min Range: -18.6590
Max Act: 16.5340. Min Act: -0.1700
Data Index: 3840670 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 18.6590. Min Range: -18.6590
Max Act: 16.4090. Min Act: -0.1700
Data Index: 627176 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 18.6590. Min Range: -18.6590
Max Act: 16.5340. Min Act: -0.1700
Data Index: 4606462 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 18.6590. Min Range: -18.6590
Max Act: 16.4090. Min Act: -0.1700
Data Index: 3207713 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 18.6590. Min Range: -18.6590
Max Act: 16.4090. Min Act: -0.1700
Data Index: 6614474 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #19