Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2934 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9899. Min Range: -6.9899
Max Act: 6.9899. Min Act: -0.1700
Data Index: 7818177 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9899. Min Range: -6.9899
Max Act: 6.6461. Min Act: -0.1700
Data Index: 2646447 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9899. Min Range: -6.9899
Max Act: 6.6461. Min Act: -0.1700
Data Index: 6087139 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9899. Min Range: -6.9899
Max Act: 6.6149. Min Act: -0.1700
Data Index: 5048356 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9899. Min Range: -6.9899
Max Act: 6.5836. Min Act: -0.1700
Data Index: 7965732 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9899. Min Range: -6.9899
Max Act: 6.5836. Min Act: -0.1700
Data Index: 8041544 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9899. Min Range: -6.9899
Max Act: 6.5836. Min Act: -0.1700
Data Index: 3917063 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9899. Min Range: -6.9899
Max Act: 6.5836. Min Act: -0.1700
Data Index: 8341610 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9899. Min Range: -6.9899
Max Act: 6.5211. Min Act: -0.1700
Data Index: 8480597 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9899. Min Range: -6.9899
Max Act: 6.5524. Min Act: -0.1700
Data Index: 7966114 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9899. Min Range: -6.9899
Max Act: 6.5524. Min Act: -0.1700
Data Index: 5716099 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9899. Min Range: -6.9899
Max Act: 6.5524. Min Act: -0.1700
Data Index: 3616658 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9899. Min Range: -6.9899
Max Act: 6.5524. Min Act: -0.1700
Data Index: 6128308 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9899. Min Range: -6.9899
Max Act: 6.5524. Min Act: -0.1700
Data Index: 6253208 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9899. Min Range: -6.9899
Max Act: 6.5524. Min Act: -0.1700
Data Index: 4993666 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9899. Min Range: -6.9899
Max Act: 6.5211. Min Act: -0.1700
Data Index: 1629797 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9899. Min Range: -6.9899
Max Act: 6.5211. Min Act: -0.1700
Data Index: 717446 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9899. Min Range: -6.9899
Max Act: 6.5211. Min Act: -0.1700
Data Index: 663642 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9899. Min Range: -6.9899
Max Act: 6.5211. Min Act: -0.1700
Data Index: 5069669 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9899. Min Range: -6.9899
Max Act: 6.4899. Min Act: -0.1700
Data Index: 4269798 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #19