Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1708 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9876. Min Range: -5.9876
Max Act: 5.9876. Min Act: -0.1700
Data Index: 5542649 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9876. Min Range: -5.9876
Max Act: 5.8939. Min Act: -0.1700
Data Index: 8588373 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9876. Min Range: -5.9876
Max Act: 5.8314. Min Act: -0.1700
Data Index: 1727530 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9876. Min Range: -5.9876
Max Act: 5.8314. Min Act: -0.1700
Data Index: 7779611 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9876. Min Range: -5.9876
Max Act: 5.8001. Min Act: -0.1700
Data Index: 7784817 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9876. Min Range: -5.9876
Max Act: 5.7689. Min Act: -0.1700
Data Index: 877039 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9876. Min Range: -5.9876
Max Act: 5.7689. Min Act: -0.1700
Data Index: 6786904 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9876. Min Range: -5.9876
Max Act: 5.7689. Min Act: -0.1700
Data Index: 1231352 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9876. Min Range: -5.9876
Max Act: 5.7376. Min Act: -0.1700
Data Index: 994008 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9876. Min Range: -5.9876
Max Act: 5.6751. Min Act: -0.1700
Data Index: 4369152 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9876. Min Range: -5.9876
Max Act: 5.6751. Min Act: -0.1700
Data Index: 3657584 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9876. Min Range: -5.9876
Max Act: 5.6439. Min Act: -0.1700
Data Index: 161329 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9876. Min Range: -5.9876
Max Act: 5.5814. Min Act: -0.1700
Data Index: 5917157 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9876. Min Range: -5.9876
Max Act: 5.6126. Min Act: -0.1700
Data Index: 2260252 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9876. Min Range: -5.9876
Max Act: 5.5814. Min Act: -0.1700
Data Index: 7626463 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9876. Min Range: -5.9876
Max Act: 5.5814. Min Act: -0.1700
Data Index: 3741021 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9876. Min Range: -5.9876
Max Act: 5.5501. Min Act: -0.1700
Data Index: 4239868 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9876. Min Range: -5.9876
Max Act: 5.5501. Min Act: -0.1700
Data Index: 2921009 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9876. Min Range: -5.9876
Max Act: 5.5501. Min Act: -0.1700
Data Index: 5115979 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9876. Min Range: -5.9876
Max Act: 5.5189. Min Act: -0.1700
Data Index: 3891572 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #19