Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3898 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7734. Min Range: -6.7734
Max Act: 6.7734. Min Act: -0.1700
Data Index: 7686217 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7734. Min Range: -6.7734
Max Act: 6.7421. Min Act: -0.1700
Data Index: 5709092 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7734. Min Range: -6.7734
Max Act: 6.7421. Min Act: -0.1700
Data Index: 5945620 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7734. Min Range: -6.7734
Max Act: 6.7421. Min Act: -0.1700
Data Index: 8808102 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7734. Min Range: -6.7734
Max Act: 6.7109. Min Act: -0.1700
Data Index: 2468673 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7734. Min Range: -6.7734
Max Act: 6.6484. Min Act: -0.1700
Data Index: 1550371 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7734. Min Range: -6.7734
Max Act: 6.6484. Min Act: -0.1700
Data Index: 5114883 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7734. Min Range: -6.7734
Max Act: 6.5859. Min Act: -0.1700
Data Index: 8748929 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7734. Min Range: -6.7734
Max Act: 6.5859. Min Act: -0.1700
Data Index: 4698897 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7734. Min Range: -6.7734
Max Act: 6.5859. Min Act: -0.1700
Data Index: 3218833 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7734. Min Range: -6.7734
Max Act: 6.5859. Min Act: -0.1700
Data Index: 1899156 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7734. Min Range: -6.7734
Max Act: 6.5859. Min Act: -0.1700
Data Index: 3502743 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7734. Min Range: -6.7734
Max Act: 6.5546. Min Act: -0.1700
Data Index: 4370789 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7734. Min Range: -6.7734
Max Act: 6.5234. Min Act: -0.1700
Data Index: 5974084 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7734. Min Range: -6.7734
Max Act: 6.5546. Min Act: -0.1700
Data Index: 1515116 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7734. Min Range: -6.7734
Max Act: 6.5234. Min Act: -0.1700
Data Index: 7676488 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7734. Min Range: -6.7734
Max Act: 6.4921. Min Act: -0.1700
Data Index: 2797058 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7734. Min Range: -6.7734
Max Act: 6.4921. Min Act: -0.1700
Data Index: 7510564 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7734. Min Range: -6.7734
Max Act: 6.4921. Min Act: -0.1700
Data Index: 6628859 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7734. Min Range: -6.7734
Max Act: 6.4921. Min Act: -0.1700
Data Index: 2036182 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #19