Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3606 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1847. Min Range: -5.1847
Max Act: 5.1847. Min Act: -0.1700
Data Index: 4814081 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1847. Min Range: -5.1847
Max Act: 5.1535. Min Act: -0.1700
Data Index: 2191230 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1847. Min Range: -5.1847
Max Act: 5.0910. Min Act: -0.1700
Data Index: 3368333 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1847. Min Range: -5.1847
Max Act: 5.0597. Min Act: -0.1700
Data Index: 2493848 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1847. Min Range: -5.1847
Max Act: 5.0597. Min Act: -0.1700
Data Index: 6447646 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1847. Min Range: -5.1847
Max Act: 5.0285. Min Act: -0.1700
Data Index: 4151992 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1847. Min Range: -5.1847
Max Act: 5.0285. Min Act: -0.1700
Data Index: 1399988 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1847. Min Range: -5.1847
Max Act: 4.9972. Min Act: -0.1700
Data Index: 8662267 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1847. Min Range: -5.1847
Max Act: 5.0285. Min Act: -0.1700
Data Index: 1595242 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1847. Min Range: -5.1847
Max Act: 5.0285. Min Act: -0.1700
Data Index: 3986802 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1847. Min Range: -5.1847
Max Act: 4.9972. Min Act: -0.1700
Data Index: 5664424 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1847. Min Range: -5.1847
Max Act: 4.9972. Min Act: -0.1700
Data Index: 3772021 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1847. Min Range: -5.1847
Max Act: 4.9972. Min Act: -0.1700
Data Index: 7072338 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1847. Min Range: -5.1847
Max Act: 4.9660. Min Act: -0.1700
Data Index: 4058545 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1847. Min Range: -5.1847
Max Act: 4.9660. Min Act: -0.1700
Data Index: 1852105 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1847. Min Range: -5.1847
Max Act: 4.9660. Min Act: -0.1700
Data Index: 2349865 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1847. Min Range: -5.1847
Max Act: 4.9660. Min Act: -0.1700
Data Index: 6128763 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1847. Min Range: -5.1847
Max Act: 4.9972. Min Act: -0.1700
Data Index: 3967893 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1847. Min Range: -5.1847
Max Act: 4.9660. Min Act: -0.1700
Data Index: 4426857 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1847. Min Range: -5.1847
Max Act: 4.9347. Min Act: -0.1700
Data Index: 868580 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #19