Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3225 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.1687. Min Range: -2.1687
Max Act: 2.1687. Min Act: -0.1700
Data Index: 2691251 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.1687. Min Range: -2.1687
Max Act: 2.0348. Min Act: -0.1700
Data Index: 2351589 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.1687. Min Range: -2.1687
Max Act: 2.0348. Min Act: -0.1700
Data Index: 1328063 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.1687. Min Range: -2.1687
Max Act: 2.0179. Min Act: -0.1700
Data Index: 4993722 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.1687. Min Range: -2.1687
Max Act: 1.9672. Min Act: -0.1700
Data Index: 2657291 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.1687. Min Range: -2.1687
Max Act: 1.9672. Min Act: -0.1700
Data Index: 8431862 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.1687. Min Range: -2.1687
Max Act: 1.9672. Min Act: -0.1700
Data Index: 8526594 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.1687. Min Range: -2.1687
Max Act: 1.9502. Min Act: -0.1700
Data Index: 2130516 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.1687. Min Range: -2.1687
Max Act: 1.9502. Min Act: -0.1700
Data Index: 5879522 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.1687. Min Range: -2.1687
Max Act: 1.9332. Min Act: -0.1700
Data Index: 2735762 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.1687. Min Range: -2.1687
Max Act: 1.9332. Min Act: -0.1700
Data Index: 5042564 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.1687. Min Range: -2.1687
Max Act: 1.8992. Min Act: -0.1700
Data Index: 7046748 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.1687. Min Range: -2.1687
Max Act: 1.8992. Min Act: -0.1700
Data Index: 6784646 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.1687. Min Range: -2.1687
Max Act: 1.8992. Min Act: -0.1700
Data Index: 5103323 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.1687. Min Range: -2.1687
Max Act: 1.8821. Min Act: -0.1700
Data Index: 7243034 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.1687. Min Range: -2.1687
Max Act: 1.8821. Min Act: -0.1700
Data Index: 4623770 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.1687. Min Range: -2.1687
Max Act: 1.8650. Min Act: -0.1700
Data Index: 2195120 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.1687. Min Range: -2.1687
Max Act: 1.8821. Min Act: -0.1700
Data Index: 1177106 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.1687. Min Range: -2.1687
Max Act: 1.8650. Min Act: -0.1700
Data Index: 6736959 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.1687. Min Range: -2.1687
Max Act: 1.8650. Min Act: -0.1700
Data Index: 499637 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #19