Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2713 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.8561. Min Range: -8.8561
Max Act: 8.8561. Min Act: -0.1700
Data Index: 1836920 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.8561. Min Range: -8.8561
Max Act: 8.2936. Min Act: -0.1700
Data Index: 3708191 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.8561. Min Range: -8.8561
Max Act: 8.1061. Min Act: -0.1700
Data Index: 8032099 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.8561. Min Range: -8.8561
Max Act: 8.0124. Min Act: -0.1700
Data Index: 3335858 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.8561. Min Range: -8.8561
Max Act: 8.0124. Min Act: -0.1700
Data Index: 5196812 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.8561. Min Range: -8.8561
Max Act: 7.9499. Min Act: -0.1700
Data Index: 5963789 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.8561. Min Range: -8.8561
Max Act: 7.8874. Min Act: -0.1700
Data Index: 2735255 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.8561. Min Range: -8.8561
Max Act: 7.8561. Min Act: -0.1700
Data Index: 2405996 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.8561. Min Range: -8.8561
Max Act: 7.7936. Min Act: -0.1700
Data Index: 2342902 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.8561. Min Range: -8.8561
Max Act: 7.7936. Min Act: -0.1700
Data Index: 4891150 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.8561. Min Range: -8.8561
Max Act: 7.7936. Min Act: -0.1700
Data Index: 2124785 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.8561. Min Range: -8.8561
Max Act: 7.7936. Min Act: -0.1700
Data Index: 8363993 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.8561. Min Range: -8.8561
Max Act: 7.8249. Min Act: -0.1700
Data Index: 6407822 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.8561. Min Range: -8.8561
Max Act: 7.7936. Min Act: -0.1700
Data Index: 4771597 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.8561. Min Range: -8.8561
Max Act: 7.7624. Min Act: -0.1700
Data Index: 8100288 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.8561. Min Range: -8.8561
Max Act: 7.6999. Min Act: -0.1700
Data Index: 5267167 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.8561. Min Range: -8.8561
Max Act: 7.6999. Min Act: -0.1700
Data Index: 8434008 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.8561. Min Range: -8.8561
Max Act: 7.7311. Min Act: -0.1700
Data Index: 4934308 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.8561. Min Range: -8.8561
Max Act: 7.7311. Min Act: -0.1700
Data Index: 6055869 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.8561. Min Range: -8.8561
Max Act: 7.6999. Min Act: -0.1700
Data Index: 3590241 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #19