Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1521 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8813. Min Range: -7.8813
Max Act: 7.8813. Min Act: -0.1700
Data Index: 2181561 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8813. Min Range: -7.8813
Max Act: 7.8188. Min Act: -0.1700
Data Index: 1261456 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8813. Min Range: -7.8813
Max Act: 7.7563. Min Act: -0.1700
Data Index: 4664905 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8813. Min Range: -7.8813
Max Act: 7.7563. Min Act: -0.1700
Data Index: 2578423 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8813. Min Range: -7.8813
Max Act: 7.6938. Min Act: -0.1700
Data Index: 6029904 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8813. Min Range: -7.8813
Max Act: 7.6938. Min Act: -0.1700
Data Index: 8168331 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8813. Min Range: -7.8813
Max Act: 7.6313. Min Act: -0.1700
Data Index: 5178557 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8813. Min Range: -7.8813
Max Act: 7.6313. Min Act: -0.1700
Data Index: 1081547 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8813. Min Range: -7.8813
Max Act: 7.6313. Min Act: -0.1700
Data Index: 5694330 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8813. Min Range: -7.8813
Max Act: 7.6313. Min Act: -0.1700
Data Index: 3134966 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8813. Min Range: -7.8813
Max Act: 7.6313. Min Act: -0.1700
Data Index: 2592286 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8813. Min Range: -7.8813
Max Act: 7.6313. Min Act: -0.1700
Data Index: 2886032 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8813. Min Range: -7.8813
Max Act: 7.6313. Min Act: -0.1700
Data Index: 2213821 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8813. Min Range: -7.8813
Max Act: 7.6313. Min Act: -0.1700
Data Index: 2580114 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8813. Min Range: -7.8813
Max Act: 7.6313. Min Act: -0.1700
Data Index: 8364042 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8813. Min Range: -7.8813
Max Act: 7.6938. Min Act: -0.1700
Data Index: 4293901 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8813. Min Range: -7.8813
Max Act: 7.5688. Min Act: -0.1700
Data Index: 3089097 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8813. Min Range: -7.8813
Max Act: 7.5688. Min Act: -0.1700
Data Index: 4941023 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8813. Min Range: -7.8813
Max Act: 7.5063. Min Act: -0.1700
Data Index: 771698 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8813. Min Range: -7.8813
Max Act: 7.5688. Min Act: -0.1700
Data Index: 7508586 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #19