Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3153 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8500. Min Range: -5.8500
Max Act: 5.8500. Min Act: -0.1700
Data Index: 2352611 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8500. Min Range: -5.8500
Max Act: 5.6938. Min Act: -0.1700
Data Index: 8798791 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8500. Min Range: -5.8500
Max Act: 5.6313. Min Act: -0.1700
Data Index: 2362843 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8500. Min Range: -5.8500
Max Act: 5.5688. Min Act: -0.1700
Data Index: 1354957 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8500. Min Range: -5.8500
Max Act: 5.5063. Min Act: -0.1700
Data Index: 2002116 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8500. Min Range: -5.8500
Max Act: 5.3813. Min Act: -0.1700
Data Index: 8780059 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8500. Min Range: -5.8500
Max Act: 5.4125. Min Act: -0.1700
Data Index: 5040907 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8500. Min Range: -5.8500
Max Act: 5.3813. Min Act: -0.1700
Data Index: 949401 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8500. Min Range: -5.8500
Max Act: 5.3813. Min Act: -0.1700
Data Index: 4387168 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8500. Min Range: -5.8500
Max Act: 5.3813. Min Act: -0.1700
Data Index: 364511 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8500. Min Range: -5.8500
Max Act: 5.3813. Min Act: -0.1700
Data Index: 356211 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8500. Min Range: -5.8500
Max Act: 5.3500. Min Act: -0.1700
Data Index: 8724049 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8500. Min Range: -5.8500
Max Act: 5.3500. Min Act: -0.1700
Data Index: 6386322 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8500. Min Range: -5.8500
Max Act: 5.3500. Min Act: -0.1700
Data Index: 7149609 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8500. Min Range: -5.8500
Max Act: 5.3500. Min Act: -0.1700
Data Index: 8440677 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8500. Min Range: -5.8500
Max Act: 5.3500. Min Act: -0.1700
Data Index: 3208739 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8500. Min Range: -5.8500
Max Act: 5.3188. Min Act: -0.1700
Data Index: 2113558 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8500. Min Range: -5.8500
Max Act: 5.3188. Min Act: -0.1700
Data Index: 4793895 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8500. Min Range: -5.8500
Max Act: 5.3188. Min Act: -0.1700
Data Index: 7346699 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8500. Min Range: -5.8500
Max Act: 5.2875. Min Act: -0.1700
Data Index: 1959389 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #19