Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4632 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9057. Min Range: -5.9057
Max Act: 5.9057. Min Act: -0.1700
Data Index: 7844519 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9057. Min Range: -5.9057
Max Act: 5.8120. Min Act: -0.1700
Data Index: 2493728 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9057. Min Range: -5.9057
Max Act: 5.6245. Min Act: -0.1700
Data Index: 203715 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9057. Min Range: -5.9057
Max Act: 5.6245. Min Act: -0.1700
Data Index: 5680374 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9057. Min Range: -5.9057
Max Act: 5.5620. Min Act: -0.1700
Data Index: 203720 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9057. Min Range: -5.9057
Max Act: 5.4995. Min Act: -0.1700
Data Index: 203716 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9057. Min Range: -5.9057
Max Act: 5.4995. Min Act: -0.1700
Data Index: 5917687 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9057. Min Range: -5.9057
Max Act: 5.4995. Min Act: -0.1700
Data Index: 6711197 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9057. Min Range: -5.9057
Max Act: 5.4682. Min Act: -0.1700
Data Index: 2266504 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9057. Min Range: -5.9057
Max Act: 5.4682. Min Act: -0.1700
Data Index: 203711 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9057. Min Range: -5.9057
Max Act: 5.4370. Min Act: -0.1700
Data Index: 2266505 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9057. Min Range: -5.9057
Max Act: 5.4370. Min Act: -0.1700
Data Index: 168806 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9057. Min Range: -5.9057
Max Act: 5.4370. Min Act: -0.1700
Data Index: 1999093 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9057. Min Range: -5.9057
Max Act: 5.4057. Min Act: -0.1700
Data Index: 203725 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9057. Min Range: -5.9057
Max Act: 5.4057. Min Act: -0.1700
Data Index: 203713 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9057. Min Range: -5.9057
Max Act: 5.3745. Min Act: -0.1700
Data Index: 6480737 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9057. Min Range: -5.9057
Max Act: 5.3432. Min Act: -0.1700
Data Index: 7719013 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9057. Min Range: -5.9057
Max Act: 5.3432. Min Act: -0.1700
Data Index: 7222071 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9057. Min Range: -5.9057
Max Act: 5.3432. Min Act: -0.1700
Data Index: 203726 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9057. Min Range: -5.9057
Max Act: 5.3432. Min Act: -0.1700
Data Index: 6392332 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #19