Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1960 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9092. Min Range: -7.9092
Max Act: 7.9092. Min Act: -0.1700
Data Index: 555118 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9092. Min Range: -7.9092
Max Act: 7.9092. Min Act: -0.1700
Data Index: 7217069 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9092. Min Range: -7.9092
Max Act: 7.9092. Min Act: -0.1700
Data Index: 7640174 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9092. Min Range: -7.9092
Max Act: 7.8467. Min Act: -0.1700
Data Index: 5491305 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9092. Min Range: -7.9092
Max Act: 7.9092. Min Act: -0.1700
Data Index: 5313806 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9092. Min Range: -7.9092
Max Act: 7.7530. Min Act: -0.1700
Data Index: 5767957 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9092. Min Range: -7.9092
Max Act: 7.7530. Min Act: -0.1700
Data Index: 5233320 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9092. Min Range: -7.9092
Max Act: 7.6905. Min Act: -0.1700
Data Index: 5394911 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9092. Min Range: -7.9092
Max Act: 7.6905. Min Act: -0.1700
Data Index: 948830 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9092. Min Range: -7.9092
Max Act: 7.6592. Min Act: -0.1700
Data Index: 8241772 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9092. Min Range: -7.9092
Max Act: 7.5655. Min Act: -0.1700
Data Index: 6047456 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9092. Min Range: -7.9092
Max Act: 7.5655. Min Act: -0.1700
Data Index: 2573654 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9092. Min Range: -7.9092
Max Act: 7.5655. Min Act: -0.1700
Data Index: 6054455 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9092. Min Range: -7.9092
Max Act: 7.5342. Min Act: -0.1700
Data Index: 6910905 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9092. Min Range: -7.9092
Max Act: 7.4717. Min Act: -0.1700
Data Index: 1300402 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9092. Min Range: -7.9092
Max Act: 7.5030. Min Act: -0.1700
Data Index: 6118226 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9092. Min Range: -7.9092
Max Act: 7.5030. Min Act: -0.1700
Data Index: 1240155 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9092. Min Range: -7.9092
Max Act: 7.5030. Min Act: -0.1700
Data Index: 2352342 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9092. Min Range: -7.9092
Max Act: 7.4717. Min Act: -0.1700
Data Index: 1759624 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9092. Min Range: -7.9092
Max Act: 7.5030. Min Act: -0.1700
Data Index: 1533636 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #19