Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5596 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4169. Min Range: -7.4169
Max Act: 7.4169. Min Act: -0.1700
Data Index: 7066901 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4169. Min Range: -7.4169
Max Act: 6.9169. Min Act: -0.1700
Data Index: 2791546 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4169. Min Range: -7.4169
Max Act: 6.9169. Min Act: -0.1700
Data Index: 2485906 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4169. Min Range: -7.4169
Max Act: 6.7294. Min Act: -0.1700
Data Index: 4783534 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4169. Min Range: -7.4169
Max Act: 6.7294. Min Act: -0.1700
Data Index: 1608924 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4169. Min Range: -7.4169
Max Act: 6.6982. Min Act: -0.1700
Data Index: 7047425 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4169. Min Range: -7.4169
Max Act: 6.6669. Min Act: -0.1700
Data Index: 5794976 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4169. Min Range: -7.4169
Max Act: 6.6669. Min Act: -0.1700
Data Index: 1488948 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4169. Min Range: -7.4169
Max Act: 6.6357. Min Act: -0.1700
Data Index: 4746244 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4169. Min Range: -7.4169
Max Act: 6.6044. Min Act: -0.1700
Data Index: 130798 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4169. Min Range: -7.4169
Max Act: 6.5732. Min Act: -0.1700
Data Index: 4893822 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4169. Min Range: -7.4169
Max Act: 6.6044. Min Act: -0.1700
Data Index: 2838530 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4169. Min Range: -7.4169
Max Act: 6.5732. Min Act: -0.1700
Data Index: 8655851 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4169. Min Range: -7.4169
Max Act: 6.5732. Min Act: -0.1700
Data Index: 2014060 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4169. Min Range: -7.4169
Max Act: 6.5419. Min Act: -0.1700
Data Index: 4673940 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4169. Min Range: -7.4169
Max Act: 6.5732. Min Act: -0.1700
Data Index: 5472902 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4169. Min Range: -7.4169
Max Act: 6.5732. Min Act: -0.1700
Data Index: 60938 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4169. Min Range: -7.4169
Max Act: 6.5419. Min Act: -0.1700
Data Index: 4733210 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4169. Min Range: -7.4169
Max Act: 6.5732. Min Act: -0.1700
Data Index: 7903533 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4169. Min Range: -7.4169
Max Act: 6.5732. Min Act: -0.1700
Data Index: 6997075 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #19