Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5202 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0807. Min Range: -6.0807
Max Act: 6.0807. Min Act: -0.1700
Data Index: 8160962 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0807. Min Range: -6.0807
Max Act: 5.9870. Min Act: -0.1700
Data Index: 3492301 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0807. Min Range: -6.0807
Max Act: 5.9557. Min Act: -0.1700
Data Index: 8494174 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0807. Min Range: -6.0807
Max Act: 5.9557. Min Act: -0.1700
Data Index: 8778592 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0807. Min Range: -6.0807
Max Act: 5.9557. Min Act: -0.1700
Data Index: 2006216 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0807. Min Range: -6.0807
Max Act: 5.9245. Min Act: -0.1700
Data Index: 5026684 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0807. Min Range: -6.0807
Max Act: 5.8932. Min Act: -0.1700
Data Index: 5281381 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0807. Min Range: -6.0807
Max Act: 5.8307. Min Act: -0.1700
Data Index: 2610087 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0807. Min Range: -6.0807
Max Act: 5.7682. Min Act: -0.1700
Data Index: 4995109 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0807. Min Range: -6.0807
Max Act: 5.7370. Min Act: -0.1700
Data Index: 3027443 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0807. Min Range: -6.0807
Max Act: 5.7370. Min Act: -0.1700
Data Index: 8556710 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0807. Min Range: -6.0807
Max Act: 5.7057. Min Act: -0.1700
Data Index: 637244 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0807. Min Range: -6.0807
Max Act: 5.7057. Min Act: -0.1700
Data Index: 8099828 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0807. Min Range: -6.0807
Max Act: 5.7057. Min Act: -0.1700
Data Index: 6882070 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0807. Min Range: -6.0807
Max Act: 5.6432. Min Act: -0.1700
Data Index: 3486667 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0807. Min Range: -6.0807
Max Act: 5.6745. Min Act: -0.1700
Data Index: 690028 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0807. Min Range: -6.0807
Max Act: 5.6745. Min Act: -0.1700
Data Index: 5123362 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0807. Min Range: -6.0807
Max Act: 5.6745. Min Act: -0.1700
Data Index: 323172 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0807. Min Range: -6.0807
Max Act: 5.6120. Min Act: -0.1700
Data Index: 7846765 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0807. Min Range: -6.0807
Max Act: 5.6120. Min Act: -0.1700
Data Index: 4075018 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #19