Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4742 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1454. Min Range: -8.1454
Max Act: 8.1454. Min Act: -0.1700
Data Index: 6596089 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1454. Min Range: -8.1454
Max Act: 7.7391. Min Act: -0.1700
Data Index: 1366599 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1454. Min Range: -8.1454
Max Act: 7.6141. Min Act: -0.1700
Data Index: 348895 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1454. Min Range: -8.1454
Max Act: 7.4266. Min Act: -0.1700
Data Index: 6667798 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1454. Min Range: -8.1454
Max Act: 7.4266. Min Act: -0.1700
Data Index: 7583899 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1454. Min Range: -8.1454
Max Act: 7.3329. Min Act: -0.1700
Data Index: 8471491 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1454. Min Range: -8.1454
Max Act: 7.3641. Min Act: -0.1700
Data Index: 6921599 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1454. Min Range: -8.1454
Max Act: 7.3329. Min Act: -0.1700
Data Index: 1818449 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1454. Min Range: -8.1454
Max Act: 7.3329. Min Act: -0.1700
Data Index: 8186514 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1454. Min Range: -8.1454
Max Act: 7.3016. Min Act: -0.1700
Data Index: 5435613 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1454. Min Range: -8.1454
Max Act: 7.2391. Min Act: -0.1700
Data Index: 5705638 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1454. Min Range: -8.1454
Max Act: 7.2391. Min Act: -0.1700
Data Index: 6018663 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1454. Min Range: -8.1454
Max Act: 7.1766. Min Act: -0.1700
Data Index: 389497 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1454. Min Range: -8.1454
Max Act: 7.1766. Min Act: -0.1700
Data Index: 3593720 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1454. Min Range: -8.1454
Max Act: 7.1766. Min Act: -0.1700
Data Index: 3445919 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1454. Min Range: -8.1454
Max Act: 7.1766. Min Act: -0.1700
Data Index: 2302136 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1454. Min Range: -8.1454
Max Act: 7.1766. Min Act: -0.1700
Data Index: 4887417 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1454. Min Range: -8.1454
Max Act: 7.0516. Min Act: -0.1700
Data Index: 499410 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1454. Min Range: -8.1454
Max Act: 7.0829. Min Act: -0.1700
Data Index: 3279940 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1454. Min Range: -8.1454
Max Act: 7.0829. Min Act: -0.1700
Data Index: 5013109 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #19