Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5095 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0201. Min Range: -8.0201
Max Act: 8.0201. Min Act: -0.1700
Data Index: 6384334 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0201. Min Range: -8.0201
Max Act: 7.7076. Min Act: -0.1700
Data Index: 2527567 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0201. Min Range: -8.0201
Max Act: 7.7076. Min Act: -0.1700
Data Index: 3458598 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0201. Min Range: -8.0201
Max Act: 7.7076. Min Act: -0.1700
Data Index: 1060489 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0201. Min Range: -8.0201
Max Act: 7.5826. Min Act: -0.1700
Data Index: 5038640 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0201. Min Range: -8.0201
Max Act: 7.5826. Min Act: -0.1700
Data Index: 1581312 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0201. Min Range: -8.0201
Max Act: 7.5826. Min Act: -0.1700
Data Index: 8365765 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0201. Min Range: -8.0201
Max Act: 7.5826. Min Act: -0.1700
Data Index: 2081664 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0201. Min Range: -8.0201
Max Act: 7.5201. Min Act: -0.1700
Data Index: 5625906 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0201. Min Range: -8.0201
Max Act: 7.5201. Min Act: -0.1700
Data Index: 35524 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0201. Min Range: -8.0201
Max Act: 7.5826. Min Act: -0.1700
Data Index: 4951388 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0201. Min Range: -8.0201
Max Act: 7.4576. Min Act: -0.1700
Data Index: 2246832 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0201. Min Range: -8.0201
Max Act: 7.4576. Min Act: -0.1700
Data Index: 3467198 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0201. Min Range: -8.0201
Max Act: 7.4576. Min Act: -0.1700
Data Index: 3401853 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0201. Min Range: -8.0201
Max Act: 7.4263. Min Act: -0.1700
Data Index: 4200966 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0201. Min Range: -8.0201
Max Act: 7.4576. Min Act: -0.1700
Data Index: 6087234 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0201. Min Range: -8.0201
Max Act: 7.4263. Min Act: -0.1700
Data Index: 2404105 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0201. Min Range: -8.0201
Max Act: 7.3951. Min Act: -0.1700
Data Index: 6428157 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0201. Min Range: -8.0201
Max Act: 7.4263. Min Act: -0.1700
Data Index: 7755933 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0201. Min Range: -8.0201
Max Act: 7.3951. Min Act: -0.1700
Data Index: 3725577 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #19