Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 396 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4876. Min Range: -8.4876
Max Act: 8.4876. Min Act: -0.1700
Data Index: 4900973 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4876. Min Range: -8.4876
Max Act: 8.1126. Min Act: -0.1700
Data Index: 5379348 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4876. Min Range: -8.4876
Max Act: 8.1126. Min Act: -0.1700
Data Index: 4696084 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4876. Min Range: -8.4876
Max Act: 8.0501. Min Act: -0.1700
Data Index: 7191422 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4876. Min Range: -8.4876
Max Act: 7.9876. Min Act: -0.1700
Data Index: 7614949 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4876. Min Range: -8.4876
Max Act: 7.9876. Min Act: -0.1700
Data Index: 6516557 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4876. Min Range: -8.4876
Max Act: 7.9876. Min Act: -0.1700
Data Index: 2353446 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4876. Min Range: -8.4876
Max Act: 7.9251. Min Act: -0.1700
Data Index: 1840246 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4876. Min Range: -8.4876
Max Act: 7.9251. Min Act: -0.1700
Data Index: 1241002 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4876. Min Range: -8.4876
Max Act: 7.8626. Min Act: -0.1700
Data Index: 4112036 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4876. Min Range: -8.4876
Max Act: 7.8001. Min Act: -0.1700
Data Index: 528221 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4876. Min Range: -8.4876
Max Act: 7.8001. Min Act: -0.1700
Data Index: 6344073 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4876. Min Range: -8.4876
Max Act: 7.8001. Min Act: -0.1700
Data Index: 8438783 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4876. Min Range: -8.4876
Max Act: 7.8001. Min Act: -0.1700
Data Index: 2455749 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4876. Min Range: -8.4876
Max Act: 7.8001. Min Act: -0.1700
Data Index: 6180714 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4876. Min Range: -8.4876
Max Act: 7.7376. Min Act: -0.1700
Data Index: 6034198 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4876. Min Range: -8.4876
Max Act: 7.7376. Min Act: -0.1700
Data Index: 2917585 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4876. Min Range: -8.4876
Max Act: 7.7376. Min Act: -0.1700
Data Index: 2100457 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4876. Min Range: -8.4876
Max Act: 7.6751. Min Act: -0.1700
Data Index: 2339167 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4876. Min Range: -8.4876
Max Act: 7.6751. Min Act: -0.1700
Data Index: 5532830 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #19