Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4056 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.8926. Min Range: -2.8926
Max Act: 2.8926. Min Act: -0.1700
Data Index: 6319635 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8926. Min Range: -2.8926
Max Act: 2.8767. Min Act: -0.1700
Data Index: 1004304 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8926. Min Range: -2.8926
Max Act: 2.8767. Min Act: -0.1700
Data Index: 1600532 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8926. Min Range: -2.8926
Max Act: 2.8767. Min Act: -0.1700
Data Index: 8646700 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8926. Min Range: -2.8926
Max Act: 2.8608. Min Act: -0.1700
Data Index: 4200292 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8926. Min Range: -2.8926
Max Act: 2.8290. Min Act: -0.1700
Data Index: 8825427 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8926. Min Range: -2.8926
Max Act: 2.8290. Min Act: -0.1700
Data Index: 2394408 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8926. Min Range: -2.8926
Max Act: 2.8290. Min Act: -0.1700
Data Index: 7329943 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8926. Min Range: -2.8926
Max Act: 2.8290. Min Act: -0.1700
Data Index: 8348520 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8926. Min Range: -2.8926
Max Act: 2.8290. Min Act: -0.1700
Data Index: 2619452 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8926. Min Range: -2.8926
Max Act: 2.8131. Min Act: -0.1700
Data Index: 78393 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8926. Min Range: -2.8926
Max Act: 2.8131. Min Act: -0.1700
Data Index: 1442251 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8926. Min Range: -2.8926
Max Act: 2.7972. Min Act: -0.1700
Data Index: 4993480 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8926. Min Range: -2.8926
Max Act: 2.8131. Min Act: -0.1700
Data Index: 2679861 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8926. Min Range: -2.8926
Max Act: 2.7813. Min Act: -0.1700
Data Index: 300802 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8926. Min Range: -2.8926
Max Act: 2.7813. Min Act: -0.1700
Data Index: 1713719 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8926. Min Range: -2.8926
Max Act: 2.7653. Min Act: -0.1700
Data Index: 3826408 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8926. Min Range: -2.8926
Max Act: 2.7653. Min Act: -0.1700
Data Index: 3120281 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8926. Min Range: -2.8926
Max Act: 2.7494. Min Act: -0.1700
Data Index: 4817406 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8926. Min Range: -2.8926
Max Act: 2.7653. Min Act: -0.1700
Data Index: 7644983 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #19