Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6005 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0032. Min Range: -6.0032
Max Act: 6.0032. Min Act: -0.1700
Data Index: 106211 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0032. Min Range: -6.0032
Max Act: 5.9720. Min Act: -0.1700
Data Index: 1160882 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0032. Min Range: -6.0032
Max Act: 5.9407. Min Act: -0.1700
Data Index: 2002044 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0032. Min Range: -6.0032
Max Act: 5.9095. Min Act: -0.1700
Data Index: 4844011 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0032. Min Range: -6.0032
Max Act: 5.8782. Min Act: -0.1700
Data Index: 2217833 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0032. Min Range: -6.0032
Max Act: 5.8782. Min Act: -0.1700
Data Index: 5046270 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0032. Min Range: -6.0032
Max Act: 5.7845. Min Act: -0.1700
Data Index: 3433119 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0032. Min Range: -6.0032
Max Act: 5.7532. Min Act: -0.1700
Data Index: 6565137 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0032. Min Range: -6.0032
Max Act: 5.7220. Min Act: -0.1700
Data Index: 833505 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0032. Min Range: -6.0032
Max Act: 5.7220. Min Act: -0.1700
Data Index: 368490 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0032. Min Range: -6.0032
Max Act: 5.6595. Min Act: -0.1700
Data Index: 8245532 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0032. Min Range: -6.0032
Max Act: 5.6595. Min Act: -0.1700
Data Index: 2144252 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0032. Min Range: -6.0032
Max Act: 5.5970. Min Act: -0.1700
Data Index: 6156660 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0032. Min Range: -6.0032
Max Act: 5.5970. Min Act: -0.1700
Data Index: 2606876 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0032. Min Range: -6.0032
Max Act: 5.5970. Min Act: -0.1700
Data Index: 2169393 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0032. Min Range: -6.0032
Max Act: 5.5970. Min Act: -0.1700
Data Index: 7785238 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0032. Min Range: -6.0032
Max Act: 5.5970. Min Act: -0.1700
Data Index: 3220966 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0032. Min Range: -6.0032
Max Act: 5.5345. Min Act: -0.1700
Data Index: 2289646 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0032. Min Range: -6.0032
Max Act: 5.5970. Min Act: -0.1700
Data Index: 3415491 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0032. Min Range: -6.0032
Max Act: 5.5657. Min Act: -0.1700
Data Index: 6632533 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #19