Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 44 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0141. Min Range: -6.0141
Max Act: 6.0141. Min Act: -0.1700
Data Index: 2602457 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0141. Min Range: -6.0141
Max Act: 5.9829. Min Act: -0.1700
Data Index: 150404 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0141. Min Range: -6.0141
Max Act: 5.8891. Min Act: -0.1700
Data Index: 6976698 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0141. Min Range: -6.0141
Max Act: 5.8266. Min Act: -0.1700
Data Index: 8045973 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0141. Min Range: -6.0141
Max Act: 5.7954. Min Act: -0.1700
Data Index: 6298396 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0141. Min Range: -6.0141
Max Act: 5.7641. Min Act: -0.1700
Data Index: 6350669 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0141. Min Range: -6.0141
Max Act: 5.7329. Min Act: -0.1700
Data Index: 7504792 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0141. Min Range: -6.0141
Max Act: 5.7016. Min Act: -0.1700
Data Index: 4496977 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0141. Min Range: -6.0141
Max Act: 5.6704. Min Act: -0.1700
Data Index: 248589 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0141. Min Range: -6.0141
Max Act: 5.7016. Min Act: -0.1700
Data Index: 4038114 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0141. Min Range: -6.0141
Max Act: 5.7016. Min Act: -0.1700
Data Index: 1619987 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0141. Min Range: -6.0141
Max Act: 5.7329. Min Act: -0.1700
Data Index: 6836222 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0141. Min Range: -6.0141
Max Act: 5.7016. Min Act: -0.1700
Data Index: 413212 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0141. Min Range: -6.0141
Max Act: 5.6704. Min Act: -0.1700
Data Index: 4979958 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0141. Min Range: -6.0141
Max Act: 5.6704. Min Act: -0.1700
Data Index: 7039858 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0141. Min Range: -6.0141
Max Act: 5.6704. Min Act: -0.1700
Data Index: 1907002 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0141. Min Range: -6.0141
Max Act: 5.6391. Min Act: -0.1700
Data Index: 7466532 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0141. Min Range: -6.0141
Max Act: 5.6391. Min Act: -0.1700
Data Index: 8525576 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0141. Min Range: -6.0141
Max Act: 5.6391. Min Act: -0.1700
Data Index: 1540228 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0141. Min Range: -6.0141
Max Act: 5.6079. Min Act: -0.1700
Data Index: 6091975 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #19