Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1775 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4517. Min Range: -8.4517
Max Act: 8.4517. Min Act: -0.1700
Data Index: 1658159 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4517. Min Range: -8.4517
Max Act: 8.1392. Min Act: -0.1700
Data Index: 4335471 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4517. Min Range: -8.4517
Max Act: 7.9517. Min Act: -0.1700
Data Index: 2623923 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4517. Min Range: -8.4517
Max Act: 7.8892. Min Act: -0.1700
Data Index: 5779455 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4517. Min Range: -8.4517
Max Act: 7.8267. Min Act: -0.1700
Data Index: 3391872 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4517. Min Range: -8.4517
Max Act: 7.7642. Min Act: -0.1700
Data Index: 2779831 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4517. Min Range: -8.4517
Max Act: 7.7642. Min Act: -0.1700
Data Index: 3760847 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4517. Min Range: -8.4517
Max Act: 7.7017. Min Act: -0.1700
Data Index: 8411200 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4517. Min Range: -8.4517
Max Act: 7.7017. Min Act: -0.1700
Data Index: 3784751 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4517. Min Range: -8.4517
Max Act: 7.7017. Min Act: -0.1700
Data Index: 5240470 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4517. Min Range: -8.4517
Max Act: 7.7017. Min Act: -0.1700
Data Index: 7652284 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4517. Min Range: -8.4517
Max Act: 7.7017. Min Act: -0.1700
Data Index: 3784745 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4517. Min Range: -8.4517
Max Act: 7.7017. Min Act: -0.1700
Data Index: 250709 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4517. Min Range: -8.4517
Max Act: 7.5767. Min Act: -0.1700
Data Index: 293638 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4517. Min Range: -8.4517
Max Act: 7.6392. Min Act: -0.1700
Data Index: 3042274 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4517. Min Range: -8.4517
Max Act: 7.7017. Min Act: -0.1700
Data Index: 5240468 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4517. Min Range: -8.4517
Max Act: 7.6392. Min Act: -0.1700
Data Index: 1798731 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4517. Min Range: -8.4517
Max Act: 7.5767. Min Act: -0.1700
Data Index: 7416181 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4517. Min Range: -8.4517
Max Act: 7.5454. Min Act: -0.1700
Data Index: 3832504 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4517. Min Range: -8.4517
Max Act: 7.5454. Min Act: -0.1700
Data Index: 8401581 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #19