Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3389 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3887. Min Range: -6.3887
Max Act: 6.3887. Min Act: -0.1700
Data Index: 2093273 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3887. Min Range: -6.3887
Max Act: 6.2324. Min Act: -0.1700
Data Index: 6140536 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3887. Min Range: -6.3887
Max Act: 6.2324. Min Act: -0.1700
Data Index: 5040300 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3887. Min Range: -6.3887
Max Act: 6.1074. Min Act: -0.1700
Data Index: 3101980 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3887. Min Range: -6.3887
Max Act: 6.0449. Min Act: -0.1700
Data Index: 2284104 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3887. Min Range: -6.3887
Max Act: 6.0449. Min Act: -0.1700
Data Index: 7763074 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3887. Min Range: -6.3887
Max Act: 6.1074. Min Act: -0.1700
Data Index: 4463828 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3887. Min Range: -6.3887
Max Act: 6.0762. Min Act: -0.1700
Data Index: 6861634 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3887. Min Range: -6.3887
Max Act: 6.0137. Min Act: -0.1700
Data Index: 8345765 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3887. Min Range: -6.3887
Max Act: 5.9824. Min Act: -0.1700
Data Index: 6312952 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3887. Min Range: -6.3887
Max Act: 5.8262. Min Act: -0.1700
Data Index: 4781750 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3887. Min Range: -6.3887
Max Act: 5.8262. Min Act: -0.1700
Data Index: 739521 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3887. Min Range: -6.3887
Max Act: 5.7637. Min Act: -0.1700
Data Index: 8759602 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3887. Min Range: -6.3887
Max Act: 5.7637. Min Act: -0.1700
Data Index: 7981990 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3887. Min Range: -6.3887
Max Act: 5.7324. Min Act: -0.1700
Data Index: 394902 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3887. Min Range: -6.3887
Max Act: 5.7324. Min Act: -0.1700
Data Index: 7386370 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3887. Min Range: -6.3887
Max Act: 5.7324. Min Act: -0.1700
Data Index: 8216142 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3887. Min Range: -6.3887
Max Act: 5.7012. Min Act: -0.1700
Data Index: 47343 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3887. Min Range: -6.3887
Max Act: 5.7324. Min Act: -0.1700
Data Index: 572084 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3887. Min Range: -6.3887
Max Act: 5.7012. Min Act: -0.1700
Data Index: 1665438 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #19