Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5583 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.8587. Min Range: -8.8587
Max Act: 8.8587. Min Act: -0.1700
Data Index: 4950278 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.8587. Min Range: -8.8587
Max Act: 8.2962. Min Act: -0.1700
Data Index: 471487 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.8587. Min Range: -8.8587
Max Act: 8.2962. Min Act: -0.1700
Data Index: 4453076 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.8587. Min Range: -8.8587
Max Act: 8.2337. Min Act: -0.1700
Data Index: 1404155 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.8587. Min Range: -8.8587
Max Act: 8.1712. Min Act: -0.1700
Data Index: 5100399 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.8587. Min Range: -8.8587
Max Act: 8.1087. Min Act: -0.1700
Data Index: 7069431 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.8587. Min Range: -8.8587
Max Act: 8.0150. Min Act: -0.1700
Data Index: 19166 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.8587. Min Range: -8.8587
Max Act: 7.9212. Min Act: -0.1700
Data Index: 4455509 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.8587. Min Range: -8.8587
Max Act: 7.8587. Min Act: -0.1700
Data Index: 7802095 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.8587. Min Range: -8.8587
Max Act: 7.8587. Min Act: -0.1700
Data Index: 3854805 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.8587. Min Range: -8.8587
Max Act: 7.7962. Min Act: -0.1700
Data Index: 7206459 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.8587. Min Range: -8.8587
Max Act: 7.7962. Min Act: -0.1700
Data Index: 2898573 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.8587. Min Range: -8.8587
Max Act: 7.7650. Min Act: -0.1700
Data Index: 3678211 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.8587. Min Range: -8.8587
Max Act: 7.7962. Min Act: -0.1700
Data Index: 4831972 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.8587. Min Range: -8.8587
Max Act: 7.7650. Min Act: -0.1700
Data Index: 8208514 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.8587. Min Range: -8.8587
Max Act: 7.7337. Min Act: -0.1700
Data Index: 6039742 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.8587. Min Range: -8.8587
Max Act: 7.7025. Min Act: -0.1700
Data Index: 2654908 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.8587. Min Range: -8.8587
Max Act: 7.6712. Min Act: -0.1700
Data Index: 2601223 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.8587. Min Range: -8.8587
Max Act: 7.7025. Min Act: -0.1700
Data Index: 1426189 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.8587. Min Range: -8.8587
Max Act: 7.7025. Min Act: -0.1700
Data Index: 922333 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #19