Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4940 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1245. Min Range: -6.1245
Max Act: 6.1245. Min Act: -0.1700
Data Index: 5155268 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1245. Min Range: -6.1245
Max Act: 6.1245. Min Act: -0.1700
Data Index: 6982546 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1245. Min Range: -6.1245
Max Act: 6.1245. Min Act: -0.1700
Data Index: 94084 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1245. Min Range: -6.1245
Max Act: 6.1245. Min Act: -0.1700
Data Index: 2173385 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1245. Min Range: -6.1245
Max Act: 6.0932. Min Act: -0.1700
Data Index: 8679663 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1245. Min Range: -6.1245
Max Act: 6.0307. Min Act: -0.1700
Data Index: 2173388 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1245. Min Range: -6.1245
Max Act: 5.9370. Min Act: -0.1700
Data Index: 819708 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1245. Min Range: -6.1245
Max Act: 5.9057. Min Act: -0.1700
Data Index: 8625690 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1245. Min Range: -6.1245
Max Act: 5.8745. Min Act: -0.1700
Data Index: 3966208 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1245. Min Range: -6.1245
Max Act: 5.9057. Min Act: -0.1700
Data Index: 8154532 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1245. Min Range: -6.1245
Max Act: 5.9057. Min Act: -0.1700
Data Index: 1512902 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1245. Min Range: -6.1245
Max Act: 5.8432. Min Act: -0.1700
Data Index: 5341835 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1245. Min Range: -6.1245
Max Act: 5.8432. Min Act: -0.1700
Data Index: 5225139 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1245. Min Range: -6.1245
Max Act: 5.8120. Min Act: -0.1700
Data Index: 1331105 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1245. Min Range: -6.1245
Max Act: 5.8120. Min Act: -0.1700
Data Index: 7189526 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1245. Min Range: -6.1245
Max Act: 5.8120. Min Act: -0.1700
Data Index: 5758014 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1245. Min Range: -6.1245
Max Act: 5.7807. Min Act: -0.1700
Data Index: 2013055 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1245. Min Range: -6.1245
Max Act: 5.7807. Min Act: -0.1700
Data Index: 5437400 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1245. Min Range: -6.1245
Max Act: 5.7495. Min Act: -0.1700
Data Index: 1373908 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1245. Min Range: -6.1245
Max Act: 5.7495. Min Act: -0.1700
Data Index: 3293784 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #19