Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1623 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.0779. Min Range: -8.0779
Max Act: 8.0779. Min Act: -0.1700
Data Index: 7870398 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0779. Min Range: -8.0779
Max Act: 7.9529. Min Act: -0.1700
Data Index: 5421750 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0779. Min Range: -8.0779
Max Act: 7.9529. Min Act: -0.1700
Data Index: 1858314 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0779. Min Range: -8.0779
Max Act: 7.8904. Min Act: -0.1700
Data Index: 8172895 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0779. Min Range: -8.0779
Max Act: 7.8904. Min Act: -0.1700
Data Index: 8746991 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0779. Min Range: -8.0779
Max Act: 7.8904. Min Act: -0.1700
Data Index: 3021046 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0779. Min Range: -8.0779
Max Act: 7.8279. Min Act: -0.1700
Data Index: 3323107 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0779. Min Range: -8.0779
Max Act: 7.8279. Min Act: -0.1700
Data Index: 4432814 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0779. Min Range: -8.0779
Max Act: 7.8279. Min Act: -0.1700
Data Index: 8387672 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0779. Min Range: -8.0779
Max Act: 7.7654. Min Act: -0.1700
Data Index: 5311863 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0779. Min Range: -8.0779
Max Act: 7.7342. Min Act: -0.1700
Data Index: 1789032 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0779. Min Range: -8.0779
Max Act: 7.7342. Min Act: -0.1700
Data Index: 7116886 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0779. Min Range: -8.0779
Max Act: 7.7029. Min Act: -0.1700
Data Index: 4621608 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0779. Min Range: -8.0779
Max Act: 7.7029. Min Act: -0.1700
Data Index: 6812877 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0779. Min Range: -8.0779
Max Act: 7.6717. Min Act: -0.1700
Data Index: 1490954 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0779. Min Range: -8.0779
Max Act: 7.6717. Min Act: -0.1700
Data Index: 236640 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0779. Min Range: -8.0779
Max Act: 7.7029. Min Act: -0.1700
Data Index: 7174444 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0779. Min Range: -8.0779
Max Act: 7.6404. Min Act: -0.1700
Data Index: 2112090 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0779. Min Range: -8.0779
Max Act: 7.6404. Min Act: -0.1700
Data Index: 2912944 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0779. Min Range: -8.0779
Max Act: 7.6404. Min Act: -0.1700
Data Index: 4862009 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #19