Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4760 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.1030. Min Range: -9.1030
Max Act: 9.1030. Min Act: -0.1700
Data Index: 1823627 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.1030. Min Range: -9.1030
Max Act: 8.4780. Min Act: -0.1700
Data Index: 5165050 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.1030. Min Range: -9.1030
Max Act: 8.4155. Min Act: -0.1700
Data Index: 5228441 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.1030. Min Range: -9.1030
Max Act: 8.1967. Min Act: -0.1700
Data Index: 2460077 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.1030. Min Range: -9.1030
Max Act: 8.1655. Min Act: -0.1700
Data Index: 6434040 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.1030. Min Range: -9.1030
Max Act: 8.0717. Min Act: -0.1700
Data Index: 6693007 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.1030. Min Range: -9.1030
Max Act: 8.0405. Min Act: -0.1700
Data Index: 1376467 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.1030. Min Range: -9.1030
Max Act: 8.0717. Min Act: -0.1700
Data Index: 1615827 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.1030. Min Range: -9.1030
Max Act: 8.0405. Min Act: -0.1700
Data Index: 2411018 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.1030. Min Range: -9.1030
Max Act: 8.0405. Min Act: -0.1700
Data Index: 6426940 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.1030. Min Range: -9.1030
Max Act: 8.0092. Min Act: -0.1700
Data Index: 4969038 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.1030. Min Range: -9.1030
Max Act: 8.0092. Min Act: -0.1700
Data Index: 980131 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.1030. Min Range: -9.1030
Max Act: 7.9780. Min Act: -0.1700
Data Index: 4772447 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.1030. Min Range: -9.1030
Max Act: 7.9467. Min Act: -0.1700
Data Index: 8375005 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.1030. Min Range: -9.1030
Max Act: 7.9780. Min Act: -0.1700
Data Index: 8526568 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.1030. Min Range: -9.1030
Max Act: 7.9155. Min Act: -0.1700
Data Index: 4936913 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.1030. Min Range: -9.1030
Max Act: 7.9155. Min Act: -0.1700
Data Index: 1529256 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.1030. Min Range: -9.1030
Max Act: 7.9155. Min Act: -0.1700
Data Index: 5594372 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.1030. Min Range: -9.1030
Max Act: 7.9155. Min Act: -0.1700
Data Index: 8128002 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.1030. Min Range: -9.1030
Max Act: 7.8842. Min Act: -0.1700
Data Index: 8151962 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #19