Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2116 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.4340. Min Range: -9.4340
Max Act: 9.4340. Min Act: -0.1700
Data Index: 6877566 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.4340. Min Range: -9.4340
Max Act: 9.3090. Min Act: -0.1700
Data Index: 8006437 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.4340. Min Range: -9.4340
Max Act: 9.1840. Min Act: -0.1700
Data Index: 5706612 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.4340. Min Range: -9.4340
Max Act: 9.1215. Min Act: -0.1700
Data Index: 1713549 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.4340. Min Range: -9.4340
Max Act: 9.1215. Min Act: -0.1700
Data Index: 448591 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.4340. Min Range: -9.4340
Max Act: 9.1840. Min Act: -0.1700
Data Index: 825318 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.4340. Min Range: -9.4340
Max Act: 8.9965. Min Act: -0.1700
Data Index: 8469284 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.4340. Min Range: -9.4340
Max Act: 8.9340. Min Act: -0.1700
Data Index: 1885772 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.4340. Min Range: -9.4340
Max Act: 8.8715. Min Act: -0.1700
Data Index: 3697532 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.4340. Min Range: -9.4340
Max Act: 8.8715. Min Act: -0.1700
Data Index: 2667255 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.4340. Min Range: -9.4340
Max Act: 8.8715. Min Act: -0.1700
Data Index: 3436267 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.4340. Min Range: -9.4340
Max Act: 8.8715. Min Act: -0.1700
Data Index: 4989029 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.4340. Min Range: -9.4340
Max Act: 8.8090. Min Act: -0.1700
Data Index: 1622807 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.4340. Min Range: -9.4340
Max Act: 8.8715. Min Act: -0.1700
Data Index: 7964833 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.4340. Min Range: -9.4340
Max Act: 8.8090. Min Act: -0.1700
Data Index: 1908734 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.4340. Min Range: -9.4340
Max Act: 8.8090. Min Act: -0.1700
Data Index: 183151 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.4340. Min Range: -9.4340
Max Act: 8.8090. Min Act: -0.1700
Data Index: 3062329 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.4340. Min Range: -9.4340
Max Act: 8.7465. Min Act: -0.1700
Data Index: 1743637 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.4340. Min Range: -9.4340
Max Act: 8.8090. Min Act: -0.1700
Data Index: 8216219 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.4340. Min Range: -9.4340
Max Act: 8.7465. Min Act: -0.1700
Data Index: 3237818 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #19