Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2991 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9205. Min Range: -4.9205
Max Act: 4.8892. Min Act: -0.1700
Data Index: 4194067 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9205. Min Range: -4.9205
Max Act: 4.9205. Min Act: -0.1700
Data Index: 5010543 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9205. Min Range: -4.9205
Max Act: 4.7955. Min Act: -0.1700
Data Index: 4376911 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9205. Min Range: -4.9205
Max Act: 4.7017. Min Act: -0.1700
Data Index: 2427172 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9205. Min Range: -4.9205
Max Act: 4.6705. Min Act: -0.1700
Data Index: 2688454 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9205. Min Range: -4.9205
Max Act: 4.6705. Min Act: -0.1700
Data Index: 6708091 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9205. Min Range: -4.9205
Max Act: 4.6080. Min Act: -0.1700
Data Index: 3220918 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9205. Min Range: -4.9205
Max Act: 4.6392. Min Act: -0.1700
Data Index: 7897104 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9205. Min Range: -4.9205
Max Act: 4.6080. Min Act: -0.1700
Data Index: 2077716 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9205. Min Range: -4.9205
Max Act: 4.6080. Min Act: -0.1700
Data Index: 7628948 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9205. Min Range: -4.9205
Max Act: 4.5767. Min Act: -0.1700
Data Index: 3613465 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9205. Min Range: -4.9205
Max Act: 4.5767. Min Act: -0.1700
Data Index: 6059795 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9205. Min Range: -4.9205
Max Act: 4.5767. Min Act: -0.1700
Data Index: 6024791 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9205. Min Range: -4.9205
Max Act: 4.5767. Min Act: -0.1700
Data Index: 6218057 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9205. Min Range: -4.9205
Max Act: 4.5767. Min Act: -0.1700
Data Index: 6293450 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9205. Min Range: -4.9205
Max Act: 4.5767. Min Act: -0.1700
Data Index: 6519579 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9205. Min Range: -4.9205
Max Act: 4.5767. Min Act: -0.1700
Data Index: 2156799 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9205. Min Range: -4.9205
Max Act: 4.5455. Min Act: -0.1700
Data Index: 2489874 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9205. Min Range: -4.9205
Max Act: 4.5767. Min Act: -0.1700
Data Index: 6284584 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9205. Min Range: -4.9205
Max Act: 4.5455. Min Act: -0.1700
Data Index: 5849600 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #19