Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3325 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6708. Min Range: -6.6708
Max Act: 6.6708. Min Act: -0.1700
Data Index: 4639988 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6708. Min Range: -6.6708
Max Act: 6.2021. Min Act: -0.1700
Data Index: 6576685 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6708. Min Range: -6.6708
Max Act: 6.1396. Min Act: -0.1700
Data Index: 1066227 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6708. Min Range: -6.6708
Max Act: 6.1396. Min Act: -0.1700
Data Index: 7784377 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6708. Min Range: -6.6708
Max Act: 6.0771. Min Act: -0.1700
Data Index: 2068940 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6708. Min Range: -6.6708
Max Act: 6.1083. Min Act: -0.1700
Data Index: 7236509 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6708. Min Range: -6.6708
Max Act: 6.1083. Min Act: -0.1700
Data Index: 3656314 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6708. Min Range: -6.6708
Max Act: 6.0771. Min Act: -0.1700
Data Index: 623708 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6708. Min Range: -6.6708
Max Act: 6.0458. Min Act: -0.1700
Data Index: 5742664 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6708. Min Range: -6.6708
Max Act: 6.0458. Min Act: -0.1700
Data Index: 1850721 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6708. Min Range: -6.6708
Max Act: 6.0458. Min Act: -0.1700
Data Index: 7687407 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6708. Min Range: -6.6708
Max Act: 6.0146. Min Act: -0.1700
Data Index: 3292038 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6708. Min Range: -6.6708
Max Act: 6.0146. Min Act: -0.1700
Data Index: 8798898 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6708. Min Range: -6.6708
Max Act: 5.9521. Min Act: -0.1700
Data Index: 3128502 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6708. Min Range: -6.6708
Max Act: 5.9833. Min Act: -0.1700
Data Index: 3070948 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6708. Min Range: -6.6708
Max Act: 5.8896. Min Act: -0.1700
Data Index: 3679388 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6708. Min Range: -6.6708
Max Act: 5.8896. Min Act: -0.1700
Data Index: 4859728 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6708. Min Range: -6.6708
Max Act: 5.8896. Min Act: -0.1700
Data Index: 2873181 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6708. Min Range: -6.6708
Max Act: 5.8583. Min Act: -0.1700
Data Index: 1072254 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6708. Min Range: -6.6708
Max Act: 5.8583. Min Act: -0.1700
Data Index: 3656313 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #19