Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3333 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3188. Min Range: -6.3188
Max Act: 6.3188. Min Act: -0.1700
Data Index: 5741318 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3188. Min Range: -6.3188
Max Act: 6.2563. Min Act: -0.1700
Data Index: 6364037 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3188. Min Range: -6.3188
Max Act: 6.2563. Min Act: -0.1700
Data Index: 2548393 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3188. Min Range: -6.3188
Max Act: 6.2251. Min Act: -0.1700
Data Index: 1924800 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3188. Min Range: -6.3188
Max Act: 6.1313. Min Act: -0.1700
Data Index: 575887 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3188. Min Range: -6.3188
Max Act: 6.1001. Min Act: -0.1700
Data Index: 4223776 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3188. Min Range: -6.3188
Max Act: 6.0376. Min Act: -0.1700
Data Index: 4607470 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3188. Min Range: -6.3188
Max Act: 5.9751. Min Act: -0.1700
Data Index: 3331356 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3188. Min Range: -6.3188
Max Act: 5.9126. Min Act: -0.1700
Data Index: 2441937 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3188. Min Range: -6.3188
Max Act: 5.9751. Min Act: -0.1700
Data Index: 6299268 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3188. Min Range: -6.3188
Max Act: 5.8813. Min Act: -0.1700
Data Index: 7796829 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3188. Min Range: -6.3188
Max Act: 5.8813. Min Act: -0.1700
Data Index: 1977871 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3188. Min Range: -6.3188
Max Act: 5.8501. Min Act: -0.1700
Data Index: 5509824 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3188. Min Range: -6.3188
Max Act: 5.8501. Min Act: -0.1700
Data Index: 7837948 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3188. Min Range: -6.3188
Max Act: 5.8501. Min Act: -0.1700
Data Index: 4923660 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3188. Min Range: -6.3188
Max Act: 5.8501. Min Act: -0.1700
Data Index: 6469048 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3188. Min Range: -6.3188
Max Act: 5.8188. Min Act: -0.1700
Data Index: 6547167 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3188. Min Range: -6.3188
Max Act: 5.8501. Min Act: -0.1700
Data Index: 2496759 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3188. Min Range: -6.3188
Max Act: 5.8188. Min Act: -0.1700
Data Index: 8186748 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3188. Min Range: -6.3188
Max Act: 5.7876. Min Act: -0.1700
Data Index: 6786700 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #19