Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5422 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.0107. Min Range: -10.0107
Max Act: 10.0107. Min Act: -0.1700
Data Index: 595652 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.0107. Min Range: -10.0107
Max Act: 9.8232. Min Act: -0.1700
Data Index: 6656376 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.0107. Min Range: -10.0107
Max Act: 9.6982. Min Act: -0.1700
Data Index: 6119278 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.0107. Min Range: -10.0107
Max Act: 9.6357. Min Act: -0.1700
Data Index: 2309068 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.0107. Min Range: -10.0107
Max Act: 9.6357. Min Act: -0.1700
Data Index: 7293179 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.0107. Min Range: -10.0107
Max Act: 9.5732. Min Act: -0.1700
Data Index: 1064396 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.0107. Min Range: -10.0107
Max Act: 9.5732. Min Act: -0.1700
Data Index: 6016586 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.0107. Min Range: -10.0107
Max Act: 9.5732. Min Act: -0.1700
Data Index: 8598807 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.0107. Min Range: -10.0107
Max Act: 9.5732. Min Act: -0.1700
Data Index: 8776799 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.0107. Min Range: -10.0107
Max Act: 9.5107. Min Act: -0.1700
Data Index: 3727639 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.0107. Min Range: -10.0107
Max Act: 9.5107. Min Act: -0.1700
Data Index: 1778086 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.0107. Min Range: -10.0107
Max Act: 9.5107. Min Act: -0.1700
Data Index: 7711195 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.0107. Min Range: -10.0107
Max Act: 9.5107. Min Act: -0.1700
Data Index: 182310 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.0107. Min Range: -10.0107
Max Act: 9.5107. Min Act: -0.1700
Data Index: 6465929 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.0107. Min Range: -10.0107
Max Act: 9.4482. Min Act: -0.1700
Data Index: 1333921 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.0107. Min Range: -10.0107
Max Act: 9.4482. Min Act: -0.1700
Data Index: 8306999 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.0107. Min Range: -10.0107
Max Act: 9.4482. Min Act: -0.1700
Data Index: 3162516 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.0107. Min Range: -10.0107
Max Act: 9.4482. Min Act: -0.1700
Data Index: 1185563 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.0107. Min Range: -10.0107
Max Act: 9.4482. Min Act: -0.1700
Data Index: 6984966 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.0107. Min Range: -10.0107
Max Act: 9.4482. Min Act: -0.1700
Data Index: 495661 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #19