Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3879 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5616. Min Range: -5.5616
Max Act: 5.5616. Min Act: -0.1700
Data Index: 2108467 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5616. Min Range: -5.5616
Max Act: 5.5616. Min Act: -0.1700
Data Index: 2198619 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5616. Min Range: -5.5616
Max Act: 5.5616. Min Act: -0.1697
Data Index: 597914 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5616. Min Range: -5.5616
Max Act: 5.5616. Min Act: -0.1700
Data Index: 1739861 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5616. Min Range: -5.5616
Max Act: 5.5616. Min Act: -0.1700
Data Index: 725530 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5616. Min Range: -5.5616
Max Act: 5.5616. Min Act: -0.1700
Data Index: 1768833 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5616. Min Range: -5.5616
Max Act: 5.5616. Min Act: -0.1700
Data Index: 2175456 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5616. Min Range: -5.5616
Max Act: 5.5616. Min Act: -0.1700
Data Index: 1630896 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5616. Min Range: -5.5616
Max Act: 5.5616. Min Act: -0.1700
Data Index: 1573113 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5616. Min Range: -5.5616
Max Act: 5.5616. Min Act: -0.1700
Data Index: 2149966 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5616. Min Range: -5.5616
Max Act: 5.5616. Min Act: -0.1700
Data Index: 1459158 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5616. Min Range: -5.5616
Max Act: 5.5616. Min Act: -0.1700
Data Index: 1042752 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5616. Min Range: -5.5616
Max Act: 5.5616. Min Act: -0.1700
Data Index: 2308783 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5616. Min Range: -5.5616
Max Act: 5.5616. Min Act: -0.1700
Data Index: 1287110 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5616. Min Range: -5.5616
Max Act: 5.5616. Min Act: -0.1700
Data Index: 1271116 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5616. Min Range: -5.5616
Max Act: 5.5616. Min Act: -0.1700
Data Index: 222734 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5616. Min Range: -5.5616
Max Act: 5.5616. Min Act: -0.1700
Data Index: 1980436 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5616. Min Range: -5.5616
Max Act: 5.5616. Min Act: -0.1700
Data Index: 1172448 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5616. Min Range: -5.5616
Max Act: 5.5616. Min Act: -0.1700
Data Index: 204916 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5616. Min Range: -5.5616
Max Act: 5.5616. Min Act: -0.1700
Data Index: 1796556 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #19