Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 324 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1828. Min Range: -7.1828
Max Act: 7.1828. Min Act: -0.1700
Data Index: 2671044 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1828. Min Range: -7.1828
Max Act: 7.0578. Min Act: -0.1700
Data Index: 6024526 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1828. Min Range: -7.1828
Max Act: 7.0578. Min Act: -0.1700
Data Index: 5067960 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1828. Min Range: -7.1828
Max Act: 6.9953. Min Act: -0.1700
Data Index: 8479236 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1828. Min Range: -7.1828
Max Act: 6.9641. Min Act: -0.1700
Data Index: 3374390 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1828. Min Range: -7.1828
Max Act: 6.9641. Min Act: -0.1700
Data Index: 6257679 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1828. Min Range: -7.1828
Max Act: 6.9016. Min Act: -0.1700
Data Index: 2882628 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1828. Min Range: -7.1828
Max Act: 6.8391. Min Act: -0.1700
Data Index: 3474247 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1828. Min Range: -7.1828
Max Act: 6.8391. Min Act: -0.1700
Data Index: 4795823 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1828. Min Range: -7.1828
Max Act: 6.8391. Min Act: -0.1700
Data Index: 2760443 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1828. Min Range: -7.1828
Max Act: 6.8078. Min Act: -0.1700
Data Index: 6257680 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1828. Min Range: -7.1828
Max Act: 6.8391. Min Act: -0.1700
Data Index: 7459929 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1828. Min Range: -7.1828
Max Act: 6.8391. Min Act: -0.1700
Data Index: 3402148 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1828. Min Range: -7.1828
Max Act: 6.8078. Min Act: -0.1700
Data Index: 5297296 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1828. Min Range: -7.1828
Max Act: 6.7766. Min Act: -0.1700
Data Index: 749901 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1828. Min Range: -7.1828
Max Act: 6.7766. Min Act: -0.1700
Data Index: 6766229 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1828. Min Range: -7.1828
Max Act: 6.7453. Min Act: -0.1700
Data Index: 8400187 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1828. Min Range: -7.1828
Max Act: 6.7453. Min Act: -0.1700
Data Index: 2671043 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1828. Min Range: -7.1828
Max Act: 6.7453. Min Act: -0.1700
Data Index: 8169564 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1828. Min Range: -7.1828
Max Act: 6.7141. Min Act: -0.1700
Data Index: 1492529 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #19