Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4510 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5813. Min Range: -5.5813
Max Act: 5.5813. Min Act: -0.1700
Data Index: 2048017 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5813. Min Range: -5.5813
Max Act: 5.5501. Min Act: -0.1700
Data Index: 1704658 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5813. Min Range: -5.5813
Max Act: 5.4251. Min Act: -0.1700
Data Index: 7150800 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5813. Min Range: -5.5813
Max Act: 5.4251. Min Act: -0.1700
Data Index: 4162640 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5813. Min Range: -5.5813
Max Act: 5.4251. Min Act: -0.1700
Data Index: 2109490 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5813. Min Range: -5.5813
Max Act: 5.4251. Min Act: -0.1700
Data Index: 5789569 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5813. Min Range: -5.5813
Max Act: 5.4251. Min Act: -0.1700
Data Index: 184603 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5813. Min Range: -5.5813
Max Act: 5.3938. Min Act: -0.1700
Data Index: 6200116 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5813. Min Range: -5.5813
Max Act: 5.3626. Min Act: -0.1700
Data Index: 6436896 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5813. Min Range: -5.5813
Max Act: 5.3626. Min Act: -0.1700
Data Index: 6340074 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5813. Min Range: -5.5813
Max Act: 5.3626. Min Act: -0.1700
Data Index: 1988759 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5813. Min Range: -5.5813
Max Act: 5.3626. Min Act: -0.1700
Data Index: 7425276 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5813. Min Range: -5.5813
Max Act: 5.3001. Min Act: -0.1700
Data Index: 5643146 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5813. Min Range: -5.5813
Max Act: 5.3001. Min Act: -0.1700
Data Index: 7774407 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5813. Min Range: -5.5813
Max Act: 5.3001. Min Act: -0.1700
Data Index: 7726230 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5813. Min Range: -5.5813
Max Act: 5.2688. Min Act: -0.1700
Data Index: 68422 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5813. Min Range: -5.5813
Max Act: 5.2376. Min Act: -0.1700
Data Index: 2134955 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5813. Min Range: -5.5813
Max Act: 5.2688. Min Act: -0.1700
Data Index: 4247287 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5813. Min Range: -5.5813
Max Act: 5.2063. Min Act: -0.1700
Data Index: 602879 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5813. Min Range: -5.5813
Max Act: 5.2063. Min Act: -0.1700
Data Index: 7302879 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #19