Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3696 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.0850. Min Range: -7.0850
Max Act: 7.0850. Min Act: -0.1700
Data Index: 7393860 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0850. Min Range: -7.0850
Max Act: 6.8663. Min Act: -0.1700
Data Index: 3098500 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0850. Min Range: -7.0850
Max Act: 6.8350. Min Act: -0.1700
Data Index: 2774143 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0850. Min Range: -7.0850
Max Act: 6.8350. Min Act: -0.1700
Data Index: 5351145 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0850. Min Range: -7.0850
Max Act: 6.8350. Min Act: -0.1700
Data Index: 7236144 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0850. Min Range: -7.0850
Max Act: 6.8350. Min Act: -0.1700
Data Index: 6779677 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0850. Min Range: -7.0850
Max Act: 6.8663. Min Act: -0.1700
Data Index: 6282032 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0850. Min Range: -7.0850
Max Act: 6.8350. Min Act: -0.1700
Data Index: 157712 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0850. Min Range: -7.0850
Max Act: 6.8350. Min Act: -0.1700
Data Index: 5498934 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0850. Min Range: -7.0850
Max Act: 6.8038. Min Act: -0.1700
Data Index: 4258311 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0850. Min Range: -7.0850
Max Act: 6.7725. Min Act: -0.1700
Data Index: 1830925 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0850. Min Range: -7.0850
Max Act: 6.8038. Min Act: -0.1700
Data Index: 2777706 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0850. Min Range: -7.0850
Max Act: 6.8038. Min Act: -0.1700
Data Index: 8809306 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0850. Min Range: -7.0850
Max Act: 6.7725. Min Act: -0.1700
Data Index: 5704003 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0850. Min Range: -7.0850
Max Act: 6.7725. Min Act: -0.1700
Data Index: 6343785 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0850. Min Range: -7.0850
Max Act: 6.7725. Min Act: -0.1700
Data Index: 389886 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0850. Min Range: -7.0850
Max Act: 6.7725. Min Act: -0.1700
Data Index: 6621231 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0850. Min Range: -7.0850
Max Act: 6.7725. Min Act: -0.1700
Data Index: 590752 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0850. Min Range: -7.0850
Max Act: 6.7725. Min Act: -0.1700
Data Index: 7788887 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0850. Min Range: -7.0850
Max Act: 6.7725. Min Act: -0.1700
Data Index: 5229241 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #19