Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2608 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 14.1035. Min Range: -14.1035
Max Act: 14.1035. Min Act: -0.1700
Data Index: 5084003 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 14.1035. Min Range: -14.1035
Max Act: 14.1035. Min Act: -0.1700
Data Index: 8476454 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 14.1035. Min Range: -14.1035
Max Act: 13.9785. Min Act: -0.1700
Data Index: 6505655 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 14.1035. Min Range: -14.1035
Max Act: 13.9160. Min Act: -0.1700
Data Index: 5754854 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 14.1035. Min Range: -14.1035
Max Act: 13.7910. Min Act: -0.1700
Data Index: 7841440 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 14.1035. Min Range: -14.1035
Max Act: 13.8535. Min Act: -0.1700
Data Index: 3602957 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 14.1035. Min Range: -14.1035
Max Act: 13.6660. Min Act: -0.1700
Data Index: 3178992 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 14.1035. Min Range: -14.1035
Max Act: 13.6035. Min Act: -0.1700
Data Index: 1379979 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 14.1035. Min Range: -14.1035
Max Act: 13.6035. Min Act: -0.1700
Data Index: 2271932 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 14.1035. Min Range: -14.1035
Max Act: 13.6035. Min Act: -0.1700
Data Index: 3935622 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 14.1035. Min Range: -14.1035
Max Act: 13.5410. Min Act: -0.1700
Data Index: 806068 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 14.1035. Min Range: -14.1035
Max Act: 13.4785. Min Act: -0.1700
Data Index: 1846528 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 14.1035. Min Range: -14.1035
Max Act: 13.4160. Min Act: -0.1700
Data Index: 5645454 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 14.1035. Min Range: -14.1035
Max Act: 13.4785. Min Act: -0.1700
Data Index: 4191041 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 14.1035. Min Range: -14.1035
Max Act: 13.4160. Min Act: -0.1700
Data Index: 7791277 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 14.1035. Min Range: -14.1035
Max Act: 13.3535. Min Act: -0.1700
Data Index: 274752 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 14.1035. Min Range: -14.1035
Max Act: 13.3535. Min Act: -0.1700
Data Index: 2587340 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 14.1035. Min Range: -14.1035
Max Act: 13.2910. Min Act: -0.1700
Data Index: 4185030 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 14.1035. Min Range: -14.1035
Max Act: 13.2285. Min Act: -0.1699
Data Index: 8425044 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 14.1035. Min Range: -14.1035
Max Act: 13.2910. Min Act: -0.1700
Data Index: 8064547 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #19