Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2991 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1061. Min Range: -8.1061
Max Act: 8.1061. Min Act: -0.1700
Data Index: 8433692 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1061. Min Range: -8.1061
Max Act: 7.9186. Min Act: -0.1700
Data Index: 6582659 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1061. Min Range: -8.1061
Max Act: 7.9811. Min Act: -0.1700
Data Index: 7480653 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1061. Min Range: -8.1061
Max Act: 7.9186. Min Act: -0.1700
Data Index: 786720 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1061. Min Range: -8.1061
Max Act: 7.9186. Min Act: -0.1700
Data Index: 6577082 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1061. Min Range: -8.1061
Max Act: 7.8561. Min Act: -0.1700
Data Index: 5549236 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1061. Min Range: -8.1061
Max Act: 7.8561. Min Act: -0.1700
Data Index: 5415981 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1061. Min Range: -8.1061
Max Act: 7.8561. Min Act: -0.1700
Data Index: 5660794 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1061. Min Range: -8.1061
Max Act: 7.7936. Min Act: -0.1700
Data Index: 7694243 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1061. Min Range: -8.1061
Max Act: 7.7311. Min Act: -0.1700
Data Index: 4756922 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1061. Min Range: -8.1061
Max Act: 7.7311. Min Act: -0.1700
Data Index: 2024947 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1061. Min Range: -8.1061
Max Act: 7.7311. Min Act: -0.1700
Data Index: 6450183 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1061. Min Range: -8.1061
Max Act: 7.7311. Min Act: -0.1700
Data Index: 345808 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1061. Min Range: -8.1061
Max Act: 7.7311. Min Act: -0.1700
Data Index: 4480163 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1061. Min Range: -8.1061
Max Act: 7.6686. Min Act: -0.1700
Data Index: 3519616 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1061. Min Range: -8.1061
Max Act: 7.6686. Min Act: -0.1700
Data Index: 1969141 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1061. Min Range: -8.1061
Max Act: 7.6686. Min Act: -0.1700
Data Index: 1718003 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1061. Min Range: -8.1061
Max Act: 7.6686. Min Act: -0.1700
Data Index: 8447876 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1061. Min Range: -8.1061
Max Act: 7.6686. Min Act: -0.1700
Data Index: 6005561 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1061. Min Range: -8.1061
Max Act: 7.6686. Min Act: -0.1700
Data Index: 8716722 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #19