Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4936 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4284. Min Range: -6.4284
Max Act: 6.4284. Min Act: -0.1700
Data Index: 730568 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4284. Min Range: -6.4284
Max Act: 6.4284. Min Act: -0.1700
Data Index: 7954902 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4284. Min Range: -6.4284
Max Act: 6.2096. Min Act: -0.1700
Data Index: 7688271 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4284. Min Range: -6.4284
Max Act: 6.1784. Min Act: -0.1700
Data Index: 2679102 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4284. Min Range: -6.4284
Max Act: 6.0846. Min Act: -0.1700
Data Index: 5527363 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4284. Min Range: -6.4284
Max Act: 6.1159. Min Act: -0.1700
Data Index: 5156029 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4284. Min Range: -6.4284
Max Act: 6.0846. Min Act: -0.1700
Data Index: 8330046 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4284. Min Range: -6.4284
Max Act: 5.9909. Min Act: -0.1700
Data Index: 6605122 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4284. Min Range: -6.4284
Max Act: 5.9596. Min Act: -0.1700
Data Index: 5731673 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4284. Min Range: -6.4284
Max Act: 5.9596. Min Act: -0.1700
Data Index: 7417142 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4284. Min Range: -6.4284
Max Act: 5.9284. Min Act: -0.1700
Data Index: 164352 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4284. Min Range: -6.4284
Max Act: 5.8971. Min Act: -0.1700
Data Index: 1049417 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4284. Min Range: -6.4284
Max Act: 5.8971. Min Act: -0.1700
Data Index: 818635 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4284. Min Range: -6.4284
Max Act: 5.8971. Min Act: -0.1700
Data Index: 1321062 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4284. Min Range: -6.4284
Max Act: 5.8971. Min Act: -0.1700
Data Index: 556034 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4284. Min Range: -6.4284
Max Act: 5.8659. Min Act: -0.1700
Data Index: 1342614 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4284. Min Range: -6.4284
Max Act: 5.8346. Min Act: -0.1700
Data Index: 8331029 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4284. Min Range: -6.4284
Max Act: 5.8034. Min Act: -0.1700
Data Index: 8515148 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4284. Min Range: -6.4284
Max Act: 5.8346. Min Act: -0.1700
Data Index: 8316141 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4284. Min Range: -6.4284
Max Act: 5.8034. Min Act: -0.1700
Data Index: 6972261 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #19