Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3457 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9009. Min Range: -4.9009
Max Act: 4.9009. Min Act: -0.1700
Data Index: 8196401 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9009. Min Range: -4.9009
Max Act: 4.8072. Min Act: -0.1700
Data Index: 151481 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9009. Min Range: -4.9009
Max Act: 4.8072. Min Act: -0.1700
Data Index: 5256917 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9009. Min Range: -4.9009
Max Act: 4.8072. Min Act: -0.1700
Data Index: 7641973 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9009. Min Range: -4.9009
Max Act: 4.8072. Min Act: -0.1700
Data Index: 4067934 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9009. Min Range: -4.9009
Max Act: 4.8072. Min Act: -0.1700
Data Index: 6487919 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9009. Min Range: -4.9009
Max Act: 4.7759. Min Act: -0.1700
Data Index: 3935097 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9009. Min Range: -4.9009
Max Act: 4.7759. Min Act: -0.1700
Data Index: 4719213 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9009. Min Range: -4.9009
Max Act: 4.7447. Min Act: -0.1700
Data Index: 5869936 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9009. Min Range: -4.9009
Max Act: 4.7447. Min Act: -0.1700
Data Index: 3775161 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9009. Min Range: -4.9009
Max Act: 4.7447. Min Act: -0.1700
Data Index: 7737200 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9009. Min Range: -4.9009
Max Act: 4.7134. Min Act: -0.1700
Data Index: 7717027 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9009. Min Range: -4.9009
Max Act: 4.6822. Min Act: -0.1700
Data Index: 5337705 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9009. Min Range: -4.9009
Max Act: 4.7134. Min Act: -0.1700
Data Index: 7697289 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9009. Min Range: -4.9009
Max Act: 4.6822. Min Act: -0.1700
Data Index: 4846828 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9009. Min Range: -4.9009
Max Act: 4.6822. Min Act: -0.1700
Data Index: 818514 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9009. Min Range: -4.9009
Max Act: 4.6509. Min Act: -0.1700
Data Index: 582556 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9009. Min Range: -4.9009
Max Act: 4.6509. Min Act: -0.1700
Data Index: 1061838 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9009. Min Range: -4.9009
Max Act: 4.6509. Min Act: -0.1700
Data Index: 5232983 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9009. Min Range: -4.9009
Max Act: 4.6509. Min Act: -0.1700
Data Index: 6228181 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #19