Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2133 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8926. Min Range: -5.8926
Max Act: 5.8926. Min Act: -0.1700
Data Index: 2778286 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8926. Min Range: -5.8926
Max Act: 5.7988. Min Act: -0.1700
Data Index: 2081765 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8926. Min Range: -5.8926
Max Act: 5.7676. Min Act: -0.1700
Data Index: 3832052 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8926. Min Range: -5.8926
Max Act: 5.7363. Min Act: -0.1700
Data Index: 1512824 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8926. Min Range: -5.8926
Max Act: 5.7051. Min Act: -0.1700
Data Index: 2211025 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8926. Min Range: -5.8926
Max Act: 5.6738. Min Act: -0.1700
Data Index: 6286043 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8926. Min Range: -5.8926
Max Act: 5.5801. Min Act: -0.1700
Data Index: 7340098 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8926. Min Range: -5.8926
Max Act: 5.6113. Min Act: -0.1700
Data Index: 3451696 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8926. Min Range: -5.8926
Max Act: 5.6113. Min Act: -0.1700
Data Index: 8543748 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8926. Min Range: -5.8926
Max Act: 5.6113. Min Act: -0.1700
Data Index: 4338117 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8926. Min Range: -5.8926
Max Act: 5.6113. Min Act: -0.1700
Data Index: 4490017 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8926. Min Range: -5.8926
Max Act: 5.6113. Min Act: -0.1700
Data Index: 4815786 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8926. Min Range: -5.8926
Max Act: 5.5801. Min Act: -0.1700
Data Index: 7313242 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8926. Min Range: -5.8926
Max Act: 5.5488. Min Act: -0.1700
Data Index: 3409218 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8926. Min Range: -5.8926
Max Act: 5.5176. Min Act: -0.1700
Data Index: 1047069 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8926. Min Range: -5.8926
Max Act: 5.5176. Min Act: -0.1700
Data Index: 8734775 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8926. Min Range: -5.8926
Max Act: 5.5176. Min Act: -0.1700
Data Index: 6962158 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8926. Min Range: -5.8926
Max Act: 5.5176. Min Act: -0.1700
Data Index: 7933489 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8926. Min Range: -5.8926
Max Act: 5.5176. Min Act: -0.1700
Data Index: 1427926 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8926. Min Range: -5.8926
Max Act: 5.4863. Min Act: -0.1700
Data Index: 2557691 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #19