Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4046 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.7687. Min Range: -3.7687
Max Act: 3.7687. Min Act: -0.1700
Data Index: 3105053 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7687. Min Range: -3.7687
Max Act: 3.7062. Min Act: -0.1700
Data Index: 1122234 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7687. Min Range: -3.7687
Max Act: 3.7062. Min Act: -0.1700
Data Index: 3256763 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7687. Min Range: -3.7687
Max Act: 3.7062. Min Act: -0.1700
Data Index: 1503319 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7687. Min Range: -3.7687
Max Act: 3.6749. Min Act: -0.1700
Data Index: 8065295 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7687. Min Range: -3.7687
Max Act: 3.6749. Min Act: -0.1700
Data Index: 646169 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7687. Min Range: -3.7687
Max Act: 3.6749. Min Act: -0.1700
Data Index: 3125321 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7687. Min Range: -3.7687
Max Act: 3.6749. Min Act: -0.1700
Data Index: 4382697 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7687. Min Range: -3.7687
Max Act: 3.6749. Min Act: -0.1700
Data Index: 7167775 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7687. Min Range: -3.7687
Max Act: 3.6749. Min Act: -0.1700
Data Index: 5638684 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7687. Min Range: -3.7687
Max Act: 3.6749. Min Act: -0.1700
Data Index: 1122211 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7687. Min Range: -3.7687
Max Act: 3.6749. Min Act: -0.1700
Data Index: 5519722 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7687. Min Range: -3.7687
Max Act: 3.6749. Min Act: -0.1700
Data Index: 1077535 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7687. Min Range: -3.7687
Max Act: 3.6749. Min Act: -0.1700
Data Index: 5185848 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7687. Min Range: -3.7687
Max Act: 3.6749. Min Act: -0.1700
Data Index: 4708393 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7687. Min Range: -3.7687
Max Act: 3.6749. Min Act: -0.1700
Data Index: 964366 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7687. Min Range: -3.7687
Max Act: 3.6436. Min Act: -0.1700
Data Index: 2088033 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7687. Min Range: -3.7687
Max Act: 3.6436. Min Act: -0.1700
Data Index: 2875381 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7687. Min Range: -3.7687
Max Act: 3.6436. Min Act: -0.1700
Data Index: 1122221 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7687. Min Range: -3.7687
Max Act: 3.6436. Min Act: -0.1700
Data Index: 3256772 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19