Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2180 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4117. Min Range: -6.4117
Max Act: 6.4117. Min Act: -0.1700
Data Index: 1847987 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4117. Min Range: -6.4117
Max Act: 6.1305. Min Act: -0.1700
Data Index: 8198825 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4117. Min Range: -6.4117
Max Act: 6.0680. Min Act: -0.1700
Data Index: 6608287 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4117. Min Range: -6.4117
Max Act: 6.0055. Min Act: -0.1700
Data Index: 1878054 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4117. Min Range: -6.4117
Max Act: 5.9742. Min Act: -0.1700
Data Index: 6391780 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4117. Min Range: -6.4117
Max Act: 5.8805. Min Act: -0.1700
Data Index: 1107545 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4117. Min Range: -6.4117
Max Act: 5.8492. Min Act: -0.1700
Data Index: 2967852 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4117. Min Range: -6.4117
Max Act: 5.8492. Min Act: -0.1700
Data Index: 1680798 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4117. Min Range: -6.4117
Max Act: 5.8180. Min Act: -0.1700
Data Index: 1244135 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4117. Min Range: -6.4117
Max Act: 5.7867. Min Act: -0.1700
Data Index: 2236123 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4117. Min Range: -6.4117
Max Act: 5.7867. Min Act: -0.1700
Data Index: 2593217 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4117. Min Range: -6.4117
Max Act: 5.7867. Min Act: -0.1700
Data Index: 7440694 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4117. Min Range: -6.4117
Max Act: 5.6930. Min Act: -0.1700
Data Index: 5858214 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4117. Min Range: -6.4117
Max Act: 5.7242. Min Act: -0.1700
Data Index: 4385670 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4117. Min Range: -6.4117
Max Act: 5.7242. Min Act: -0.1700
Data Index: 5771660 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4117. Min Range: -6.4117
Max Act: 5.7555. Min Act: -0.1700
Data Index: 1604169 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4117. Min Range: -6.4117
Max Act: 5.6930. Min Act: -0.1700
Data Index: 3306103 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4117. Min Range: -6.4117
Max Act: 5.6617. Min Act: -0.1700
Data Index: 3137977 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4117. Min Range: -6.4117
Max Act: 5.6617. Min Act: -0.1700
Data Index: 6078581 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4117. Min Range: -6.4117
Max Act: 5.6617. Min Act: -0.1700
Data Index: 7312216 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #19