Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2870 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.9752. Min Range: -2.9752
Max Act: 2.9752. Min Act: -0.1700
Data Index: 5553009 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9752. Min Range: -2.9752
Max Act: 2.9119. Min Act: -0.1700
Data Index: 2734051 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9752. Min Range: -2.9752
Max Act: 2.9119. Min Act: -0.1700
Data Index: 773790 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9752. Min Range: -2.9752
Max Act: 2.8643. Min Act: -0.1700
Data Index: 5553011 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9752. Min Range: -2.9752
Max Act: 2.8484. Min Act: -0.1700
Data Index: 4522966 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9752. Min Range: -2.9752
Max Act: 2.8325. Min Act: -0.1700
Data Index: 773792 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9752. Min Range: -2.9752
Max Act: 2.8007. Min Act: -0.1700
Data Index: 6571297 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9752. Min Range: -2.9752
Max Act: 2.7848. Min Act: -0.1700
Data Index: 2001452 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9752. Min Range: -2.9752
Max Act: 2.7848. Min Act: -0.1700
Data Index: 7186644 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9752. Min Range: -2.9752
Max Act: 2.7848. Min Act: -0.1700
Data Index: 773793 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9752. Min Range: -2.9752
Max Act: 2.7848. Min Act: -0.1700
Data Index: 5553008 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9752. Min Range: -2.9752
Max Act: 2.7369. Min Act: -0.1700
Data Index: 8093656 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9752. Min Range: -2.9752
Max Act: 2.7369. Min Act: -0.1700
Data Index: 3997839 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9752. Min Range: -2.9752
Max Act: 2.7209. Min Act: -0.1700
Data Index: 773789 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9752. Min Range: -2.9752
Max Act: 2.7049. Min Act: -0.1700
Data Index: 6809450 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9752. Min Range: -2.9752
Max Act: 2.6889. Min Act: -0.1700
Data Index: 2409909 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9752. Min Range: -2.9752
Max Act: 2.6889. Min Act: -0.1700
Data Index: 7756186 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9752. Min Range: -2.9752
Max Act: 2.6729. Min Act: -0.1700
Data Index: 773788 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9752. Min Range: -2.9752
Max Act: 2.6569. Min Act: -0.1700
Data Index: 3055903 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9752. Min Range: -2.9752
Max Act: 2.6569. Min Act: -0.1700
Data Index: 1635543 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #19