Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1908 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.9317. Min Range: -2.9317
Max Act: 2.9317. Min Act: -0.1700
Data Index: 944138 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9317. Min Range: -2.9317
Max Act: 2.8047. Min Act: -0.1700
Data Index: 944137 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9317. Min Range: -2.9317
Max Act: 2.8047. Min Act: -0.1700
Data Index: 6333844 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9317. Min Range: -2.9317
Max Act: 2.8047. Min Act: -0.1700
Data Index: 6951608 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9317. Min Range: -2.9317
Max Act: 2.7888. Min Act: -0.1700
Data Index: 3436771 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9317. Min Range: -2.9317
Max Act: 2.7888. Min Act: -0.1700
Data Index: 3948785 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9317. Min Range: -2.9317
Max Act: 2.7728. Min Act: -0.1700
Data Index: 8226183 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9317. Min Range: -2.9317
Max Act: 2.7569. Min Act: -0.1700
Data Index: 5821024 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9317. Min Range: -2.9317
Max Act: 2.7569. Min Act: -0.1700
Data Index: 5678594 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9317. Min Range: -2.9317
Max Act: 2.7409. Min Act: -0.1700
Data Index: 8153249 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9317. Min Range: -2.9317
Max Act: 2.7409. Min Act: -0.1700
Data Index: 5898162 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9317. Min Range: -2.9317
Max Act: 2.7409. Min Act: -0.1700
Data Index: 6792960 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9317. Min Range: -2.9317
Max Act: 2.7250. Min Act: -0.1700
Data Index: 7911041 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9317. Min Range: -2.9317
Max Act: 2.7250. Min Act: -0.1700
Data Index: 6315597 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9317. Min Range: -2.9317
Max Act: 2.7090. Min Act: -0.1700
Data Index: 377999 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9317. Min Range: -2.9317
Max Act: 2.7090. Min Act: -0.1700
Data Index: 7786403 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9317. Min Range: -2.9317
Max Act: 2.7090. Min Act: -0.1700
Data Index: 6909264 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9317. Min Range: -2.9317
Max Act: 2.7090. Min Act: -0.1700
Data Index: 2120432 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9317. Min Range: -2.9317
Max Act: 2.7090. Min Act: -0.1700
Data Index: 568547 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9317. Min Range: -2.9317
Max Act: 2.6930. Min Act: -0.1700
Data Index: 3004479 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19