Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 901 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4517. Min Range: -5.4517
Max Act: 5.4517. Min Act: -0.1700
Data Index: 489373 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4517. Min Range: -5.4517
Max Act: 5.3580. Min Act: -0.1700
Data Index: 7585863 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4517. Min Range: -5.4517
Max Act: 5.3580. Min Act: -0.1700
Data Index: 8579152 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4517. Min Range: -5.4517
Max Act: 5.3580. Min Act: -0.1700
Data Index: 6887868 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4517. Min Range: -5.4517
Max Act: 5.3267. Min Act: -0.1700
Data Index: 8496381 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4517. Min Range: -5.4517
Max Act: 5.2642. Min Act: -0.1700
Data Index: 467997 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4517. Min Range: -5.4517
Max Act: 5.2642. Min Act: -0.1700
Data Index: 5403688 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4517. Min Range: -5.4517
Max Act: 5.2017. Min Act: -0.1700
Data Index: 6821236 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4517. Min Range: -5.4517
Max Act: 5.2017. Min Act: -0.1700
Data Index: 3931576 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4517. Min Range: -5.4517
Max Act: 5.1705. Min Act: -0.1700
Data Index: 4975701 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4517. Min Range: -5.4517
Max Act: 5.1705. Min Act: -0.1700
Data Index: 5056290 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4517. Min Range: -5.4517
Max Act: 5.1392. Min Act: -0.1700
Data Index: 5368475 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4517. Min Range: -5.4517
Max Act: 5.1080. Min Act: -0.1700
Data Index: 3400415 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4517. Min Range: -5.4517
Max Act: 5.1080. Min Act: -0.1700
Data Index: 859150 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4517. Min Range: -5.4517
Max Act: 5.1080. Min Act: -0.1700
Data Index: 3568206 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4517. Min Range: -5.4517
Max Act: 5.1080. Min Act: -0.1700
Data Index: 6446609 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4517. Min Range: -5.4517
Max Act: 5.1080. Min Act: -0.1700
Data Index: 2407635 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4517. Min Range: -5.4517
Max Act: 5.0767. Min Act: -0.1700
Data Index: 7623100 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4517. Min Range: -5.4517
Max Act: 5.0455. Min Act: -0.1700
Data Index: 5737275 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4517. Min Range: -5.4517
Max Act: 5.1080. Min Act: -0.1700
Data Index: 1290057 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #19