Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2933 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5829. Min Range: -4.5829
Max Act: 4.5829. Min Act: -0.1700
Data Index: 5386859 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5829. Min Range: -4.5829
Max Act: 4.3641. Min Act: -0.1700
Data Index: 3837301 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5829. Min Range: -4.5829
Max Act: 4.3016. Min Act: -0.1700
Data Index: 2356965 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5829. Min Range: -4.5829
Max Act: 4.2078. Min Act: -0.1700
Data Index: 7003116 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5829. Min Range: -4.5829
Max Act: 4.1766. Min Act: -0.1700
Data Index: 1042608 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5829. Min Range: -4.5829
Max Act: 4.1766. Min Act: -0.1700
Data Index: 2898869 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5829. Min Range: -4.5829
Max Act: 4.1766. Min Act: -0.1700
Data Index: 4111619 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5829. Min Range: -4.5829
Max Act: 4.1766. Min Act: -0.1700
Data Index: 726770 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5829. Min Range: -4.5829
Max Act: 4.1141. Min Act: -0.1700
Data Index: 8059958 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5829. Min Range: -4.5829
Max Act: 4.1453. Min Act: -0.1700
Data Index: 1699492 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5829. Min Range: -4.5829
Max Act: 4.1141. Min Act: -0.1700
Data Index: 2242501 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5829. Min Range: -4.5829
Max Act: 4.1453. Min Act: -0.1700
Data Index: 863457 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5829. Min Range: -4.5829
Max Act: 4.1141. Min Act: -0.1700
Data Index: 3295349 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5829. Min Range: -4.5829
Max Act: 4.0828. Min Act: -0.1700
Data Index: 1076454 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5829. Min Range: -4.5829
Max Act: 4.0516. Min Act: -0.1700
Data Index: 2852699 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5829. Min Range: -4.5829
Max Act: 4.0516. Min Act: -0.1700
Data Index: 2657020 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5829. Min Range: -4.5829
Max Act: 4.0516. Min Act: -0.1700
Data Index: 7873596 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5829. Min Range: -4.5829
Max Act: 4.0516. Min Act: -0.1700
Data Index: 1521824 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5829. Min Range: -4.5829
Max Act: 4.0516. Min Act: -0.1700
Data Index: 3298808 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5829. Min Range: -4.5829
Max Act: 4.0516. Min Act: -0.1700
Data Index: 836636 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #19