Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1267 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9159. Min Range: -7.9159
Max Act: 7.9159. Min Act: -0.1700
Data Index: 6264931 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9159. Min Range: -7.9159
Max Act: 7.7909. Min Act: -0.1700
Data Index: 2936092 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9159. Min Range: -7.9159
Max Act: 7.7909. Min Act: -0.1700
Data Index: 6727605 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9159. Min Range: -7.9159
Max Act: 7.7909. Min Act: -0.1700
Data Index: 2144753 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9159. Min Range: -7.9159
Max Act: 7.7909. Min Act: -0.1700
Data Index: 3127059 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9159. Min Range: -7.9159
Max Act: 7.7284. Min Act: -0.1700
Data Index: 3019476 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9159. Min Range: -7.9159
Max Act: 7.7284. Min Act: -0.1700
Data Index: 8772766 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9159. Min Range: -7.9159
Max Act: 7.7284. Min Act: -0.1700
Data Index: 5889021 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9159. Min Range: -7.9159
Max Act: 7.7284. Min Act: -0.1700
Data Index: 276088 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9159. Min Range: -7.9159
Max Act: 7.6659. Min Act: -0.1700
Data Index: 8165148 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9159. Min Range: -7.9159
Max Act: 7.6034. Min Act: -0.1700
Data Index: 7085582 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9159. Min Range: -7.9159
Max Act: 7.6034. Min Act: -0.1700
Data Index: 8110329 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9159. Min Range: -7.9159
Max Act: 7.6034. Min Act: -0.1700
Data Index: 5413674 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9159. Min Range: -7.9159
Max Act: 7.6034. Min Act: -0.1700
Data Index: 1465647 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9159. Min Range: -7.9159
Max Act: 7.5721. Min Act: -0.1700
Data Index: 6075114 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9159. Min Range: -7.9159
Max Act: 7.5721. Min Act: -0.1700
Data Index: 4552490 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9159. Min Range: -7.9159
Max Act: 7.5409. Min Act: -0.1700
Data Index: 776819 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9159. Min Range: -7.9159
Max Act: 7.5096. Min Act: -0.1700
Data Index: 6264929 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9159. Min Range: -7.9159
Max Act: 7.5096. Min Act: -0.1700
Data Index: 5082706 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9159. Min Range: -7.9159
Max Act: 7.5096. Min Act: -0.1700
Data Index: 8760766 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #19