Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5564 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9929. Min Range: -5.9929
Max Act: 5.9929. Min Act: -0.1700
Data Index: 6847698 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9929. Min Range: -5.9929
Max Act: 5.9929. Min Act: -0.1700
Data Index: 73794 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9929. Min Range: -5.9929
Max Act: 5.8992. Min Act: -0.1700
Data Index: 2929108 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9929. Min Range: -5.9929
Max Act: 5.8679. Min Act: -0.1700
Data Index: 6658146 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9929. Min Range: -5.9929
Max Act: 5.7429. Min Act: -0.1700
Data Index: 402331 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9929. Min Range: -5.9929
Max Act: 5.7117. Min Act: -0.1700
Data Index: 3522281 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9929. Min Range: -5.9929
Max Act: 5.7429. Min Act: -0.1700
Data Index: 4173510 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9929. Min Range: -5.9929
Max Act: 5.7117. Min Act: -0.1700
Data Index: 800047 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9929. Min Range: -5.9929
Max Act: 5.6804. Min Act: -0.1700
Data Index: 4055768 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9929. Min Range: -5.9929
Max Act: 5.6804. Min Act: -0.1700
Data Index: 2369886 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9929. Min Range: -5.9929
Max Act: 5.6492. Min Act: -0.1700
Data Index: 855697 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9929. Min Range: -5.9929
Max Act: 5.6492. Min Act: -0.1700
Data Index: 7369556 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9929. Min Range: -5.9929
Max Act: 5.6804. Min Act: -0.1700
Data Index: 3611995 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9929. Min Range: -5.9929
Max Act: 5.6804. Min Act: -0.1700
Data Index: 7968590 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9929. Min Range: -5.9929
Max Act: 5.6492. Min Act: -0.1700
Data Index: 3667262 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9929. Min Range: -5.9929
Max Act: 5.6179. Min Act: -0.1700
Data Index: 2910734 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9929. Min Range: -5.9929
Max Act: 5.6179. Min Act: -0.1700
Data Index: 1165963 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9929. Min Range: -5.9929
Max Act: 5.5867. Min Act: -0.1700
Data Index: 2838609 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9929. Min Range: -5.9929
Max Act: 5.5867. Min Act: -0.1700
Data Index: 690622 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9929. Min Range: -5.9929
Max Act: 5.5867. Min Act: -0.1700
Data Index: 8582026 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #19