Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5195 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1938. Min Range: -6.1938
Max Act: 6.1938. Min Act: -0.1700
Data Index: 913084 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1938. Min Range: -6.1938
Max Act: 6.1001. Min Act: -0.1700
Data Index: 7850364 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1938. Min Range: -6.1938
Max Act: 6.0376. Min Act: -0.1700
Data Index: 4350299 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1938. Min Range: -6.1938
Max Act: 5.9751. Min Act: -0.1700
Data Index: 8056727 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1938. Min Range: -6.1938
Max Act: 6.0063. Min Act: -0.1700
Data Index: 8571949 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1938. Min Range: -6.1938
Max Act: 5.9126. Min Act: -0.1700
Data Index: 3565714 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1938. Min Range: -6.1938
Max Act: 5.8813. Min Act: -0.1700
Data Index: 8812898 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1938. Min Range: -6.1938
Max Act: 5.8188. Min Act: -0.1700
Data Index: 3866704 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1938. Min Range: -6.1938
Max Act: 5.8501. Min Act: -0.1700
Data Index: 2559090 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1938. Min Range: -6.1938
Max Act: 5.7876. Min Act: -0.1700
Data Index: 4798167 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1938. Min Range: -6.1938
Max Act: 5.7563. Min Act: -0.1700
Data Index: 2875127 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1938. Min Range: -6.1938
Max Act: 5.7563. Min Act: -0.1700
Data Index: 4613426 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1938. Min Range: -6.1938
Max Act: 5.7563. Min Act: -0.1700
Data Index: 2205902 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1938. Min Range: -6.1938
Max Act: 5.7251. Min Act: -0.1700
Data Index: 3813256 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1938. Min Range: -6.1938
Max Act: 5.7251. Min Act: -0.1700
Data Index: 6393471 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1938. Min Range: -6.1938
Max Act: 5.6938. Min Act: -0.1700
Data Index: 4490071 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1938. Min Range: -6.1938
Max Act: 5.6938. Min Act: -0.1700
Data Index: 6060777 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1938. Min Range: -6.1938
Max Act: 5.6938. Min Act: -0.1700
Data Index: 1248502 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1938. Min Range: -6.1938
Max Act: 5.6938. Min Act: -0.1700
Data Index: 2129733 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1938. Min Range: -6.1938
Max Act: 5.6938. Min Act: -0.1700
Data Index: 6031143 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #19