Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5236 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0767. Min Range: -6.0767
Max Act: 6.0767. Min Act: -0.1700
Data Index: 1357064 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0767. Min Range: -6.0767
Max Act: 5.8267. Min Act: -0.1700
Data Index: 6591741 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0767. Min Range: -6.0767
Max Act: 5.7642. Min Act: -0.1700
Data Index: 6992989 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0767. Min Range: -6.0767
Max Act: 5.7330. Min Act: -0.1700
Data Index: 1032099 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0767. Min Range: -6.0767
Max Act: 5.7330. Min Act: -0.1700
Data Index: 4313935 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0767. Min Range: -6.0767
Max Act: 5.6705. Min Act: -0.1700
Data Index: 7707970 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0767. Min Range: -6.0767
Max Act: 5.6705. Min Act: -0.1700
Data Index: 471992 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0767. Min Range: -6.0767
Max Act: 5.6392. Min Act: -0.1700
Data Index: 6591751 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0767. Min Range: -6.0767
Max Act: 5.6080. Min Act: -0.1700
Data Index: 6421841 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0767. Min Range: -6.0767
Max Act: 5.6080. Min Act: -0.1698
Data Index: 6878744 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0767. Min Range: -6.0767
Max Act: 5.5767. Min Act: -0.1700
Data Index: 6878745 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0767. Min Range: -6.0767
Max Act: 5.6080. Min Act: -0.1700
Data Index: 778471 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0767. Min Range: -6.0767
Max Act: 5.6080. Min Act: -0.1700
Data Index: 4070798 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0767. Min Range: -6.0767
Max Act: 5.6392. Min Act: -0.1699
Data Index: 8058098 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0767. Min Range: -6.0767
Max Act: 5.5767. Min Act: -0.1700
Data Index: 1467005 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0767. Min Range: -6.0767
Max Act: 5.5767. Min Act: -0.1700
Data Index: 4074965 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0767. Min Range: -6.0767
Max Act: 5.5767. Min Act: -0.1700
Data Index: 4976706 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0767. Min Range: -6.0767
Max Act: 5.5767. Min Act: -0.1700
Data Index: 5145129 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0767. Min Range: -6.0767
Max Act: 5.5455. Min Act: -0.1700
Data Index: 1032100 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0767. Min Range: -6.0767
Max Act: 5.5142. Min Act: -0.1700
Data Index: 6591745 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #19