Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1024 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.0812. Min Range: -8.0812
Max Act: 7.9562. Min Act: -0.1700
Data Index: 2780449 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0812. Min Range: -8.0812
Max Act: 8.0499. Min Act: -0.1700
Data Index: 5618482 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0812. Min Range: -8.0812
Max Act: 8.0499. Min Act: -0.1700
Data Index: 8533415 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0812. Min Range: -8.0812
Max Act: 8.0812. Min Act: -0.1700
Data Index: 8646058 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0812. Min Range: -8.0812
Max Act: 7.9562. Min Act: -0.1700
Data Index: 2884525 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0812. Min Range: -8.0812
Max Act: 7.9874. Min Act: -0.1700
Data Index: 6412622 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0812. Min Range: -8.0812
Max Act: 7.9249. Min Act: -0.1700
Data Index: 5069153 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0812. Min Range: -8.0812
Max Act: 7.7687. Min Act: -0.1700
Data Index: 2036751 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0812. Min Range: -8.0812
Max Act: 7.7374. Min Act: -0.1700
Data Index: 8702200 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0812. Min Range: -8.0812
Max Act: 7.7062. Min Act: -0.1700
Data Index: 5856095 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0812. Min Range: -8.0812
Max Act: 7.7374. Min Act: -0.1700
Data Index: 1955123 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0812. Min Range: -8.0812
Max Act: 7.6124. Min Act: -0.1700
Data Index: 7087522 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0812. Min Range: -8.0812
Max Act: 7.6749. Min Act: -0.1700
Data Index: 6453773 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0812. Min Range: -8.0812
Max Act: 7.6749. Min Act: -0.1700
Data Index: 1505378 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0812. Min Range: -8.0812
Max Act: 7.5812. Min Act: -0.1700
Data Index: 1220677 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0812. Min Range: -8.0812
Max Act: 7.6124. Min Act: -0.1700
Data Index: 980654 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0812. Min Range: -8.0812
Max Act: 7.5812. Min Act: -0.1700
Data Index: 809238 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0812. Min Range: -8.0812
Max Act: 7.6437. Min Act: -0.1700
Data Index: 757815 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0812. Min Range: -8.0812
Max Act: 7.5499. Min Act: -0.1700
Data Index: 937005 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0812. Min Range: -8.0812
Max Act: 7.5812. Min Act: -0.1700
Data Index: 5837364 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #19