Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3521 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3014. Min Range: -6.3014
Max Act: 6.3014. Min Act: -0.1700
Data Index: 7762556 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3014. Min Range: -6.3014
Max Act: 6.0514. Min Act: -0.1700
Data Index: 6420333 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3014. Min Range: -6.3014
Max Act: 6.0201. Min Act: -0.1700
Data Index: 6372787 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3014. Min Range: -6.3014
Max Act: 5.9889. Min Act: -0.1700
Data Index: 7787566 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3014. Min Range: -6.3014
Max Act: 5.9576. Min Act: -0.1700
Data Index: 5492945 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3014. Min Range: -6.3014
Max Act: 5.9576. Min Act: -0.1700
Data Index: 6736343 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3014. Min Range: -6.3014
Max Act: 5.9576. Min Act: -0.1700
Data Index: 1859171 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3014. Min Range: -6.3014
Max Act: 5.9576. Min Act: -0.1700
Data Index: 6531941 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3014. Min Range: -6.3014
Max Act: 5.9264. Min Act: -0.1700
Data Index: 4945555 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3014. Min Range: -6.3014
Max Act: 5.9264. Min Act: -0.1700
Data Index: 3863021 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3014. Min Range: -6.3014
Max Act: 5.8639. Min Act: -0.1700
Data Index: 3752170 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3014. Min Range: -6.3014
Max Act: 5.8326. Min Act: -0.1700
Data Index: 5651088 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3014. Min Range: -6.3014
Max Act: 5.8326. Min Act: -0.1700
Data Index: 6783268 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3014. Min Range: -6.3014
Max Act: 5.8014. Min Act: -0.1700
Data Index: 685092 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3014. Min Range: -6.3014
Max Act: 5.8014. Min Act: -0.1700
Data Index: 4223031 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3014. Min Range: -6.3014
Max Act: 5.8014. Min Act: -0.1700
Data Index: 7095074 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3014. Min Range: -6.3014
Max Act: 5.8014. Min Act: -0.1700
Data Index: 6454374 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3014. Min Range: -6.3014
Max Act: 5.8014. Min Act: -0.1700
Data Index: 1381844 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3014. Min Range: -6.3014
Max Act: 5.7701. Min Act: -0.1700
Data Index: 8789683 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3014. Min Range: -6.3014
Max Act: 5.7701. Min Act: -0.1700
Data Index: 5752297 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #19