Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2554 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.6118. Min Range: -1.6118
Max Act: 1.6118. Min Act: -0.1700
Data Index: 33006 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.6118. Min Range: -1.6118
Max Act: 1.6118. Min Act: -0.1700
Data Index: 5682229 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.6118. Min Range: -1.6118
Max Act: 1.5594. Min Act: -0.1700
Data Index: 6053276 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.6118. Min Range: -1.6118
Max Act: 1.5418. Min Act: -0.1700
Data Index: 1011502 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.6118. Min Range: -1.6118
Max Act: 1.5418. Min Act: -0.1700
Data Index: 6452072 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.6118. Min Range: -1.6118
Max Act: 1.5418. Min Act: -0.1700
Data Index: 6729128 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.6118. Min Range: -1.6118
Max Act: 1.5243. Min Act: -0.1700
Data Index: 8824301 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.6118. Min Range: -1.6118
Max Act: 1.5243. Min Act: -0.1700
Data Index: 6062692 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.6118. Min Range: -1.6118
Max Act: 1.5243. Min Act: -0.1700
Data Index: 5682226 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.6118. Min Range: -1.6118
Max Act: 1.5418. Min Act: -0.1700
Data Index: 1916889 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.6118. Min Range: -1.6118
Max Act: 1.5243. Min Act: -0.1700
Data Index: 8713626 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.6118. Min Range: -1.6118
Max Act: 1.5243. Min Act: -0.1700
Data Index: 1892227 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.6118. Min Range: -1.6118
Max Act: 1.5068. Min Act: -0.1700
Data Index: 5992408 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.6118. Min Range: -1.6118
Max Act: 1.5068. Min Act: -0.1700
Data Index: 7302747 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.6118. Min Range: -1.6118
Max Act: 1.5068. Min Act: -0.1700
Data Index: 430165 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.6118. Min Range: -1.6118
Max Act: 1.5068. Min Act: -0.1700
Data Index: 1885453 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.6118. Min Range: -1.6118
Max Act: 1.5068. Min Act: -0.1700
Data Index: 451126 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.6118. Min Range: -1.6118
Max Act: 1.5068. Min Act: -0.1700
Data Index: 6532011 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.6118. Min Range: -1.6118
Max Act: 1.5068. Min Act: -0.1700
Data Index: 3140103 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.6118. Min Range: -1.6118
Max Act: 1.5068. Min Act: -0.1700
Data Index: 5889453 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #19