Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2899 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9896. Min Range: -4.9896
Max Act: 4.9896. Min Act: -0.1700
Data Index: 2221435 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9896. Min Range: -4.9896
Max Act: 4.7708. Min Act: -0.1700
Data Index: 190564 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9896. Min Range: -4.9896
Max Act: 4.7396. Min Act: -0.1700
Data Index: 8664215 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9896. Min Range: -4.9896
Max Act: 4.7396. Min Act: -0.1700
Data Index: 3139819 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9896. Min Range: -4.9896
Max Act: 4.7083. Min Act: -0.1700
Data Index: 202349 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9896. Min Range: -4.9896
Max Act: 4.6458. Min Act: -0.1700
Data Index: 3689513 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9896. Min Range: -4.9896
Max Act: 4.6458. Min Act: -0.1700
Data Index: 5965155 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9896. Min Range: -4.9896
Max Act: 4.6458. Min Act: -0.1700
Data Index: 6982504 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9896. Min Range: -4.9896
Max Act: 4.6458. Min Act: -0.1700
Data Index: 8500070 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9896. Min Range: -4.9896
Max Act: 4.6458. Min Act: -0.1700
Data Index: 6726876 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9896. Min Range: -4.9896
Max Act: 4.6146. Min Act: -0.1700
Data Index: 5331675 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9896. Min Range: -4.9896
Max Act: 4.6146. Min Act: -0.1700
Data Index: 5244783 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9896. Min Range: -4.9896
Max Act: 4.5208. Min Act: -0.1700
Data Index: 6632292 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9896. Min Range: -4.9896
Max Act: 4.5208. Min Act: -0.1700
Data Index: 5812147 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9896. Min Range: -4.9896
Max Act: 4.5208. Min Act: -0.1700
Data Index: 1021868 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9896. Min Range: -4.9896
Max Act: 4.4895. Min Act: -0.1700
Data Index: 1621961 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9896. Min Range: -4.9896
Max Act: 4.5208. Min Act: -0.1700
Data Index: 4929937 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9896. Min Range: -4.9896
Max Act: 4.4895. Min Act: -0.1700
Data Index: 6272226 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9896. Min Range: -4.9896
Max Act: 4.4270. Min Act: -0.1700
Data Index: 5415769 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9896. Min Range: -4.9896
Max Act: 4.4583. Min Act: -0.1700
Data Index: 7183944 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #19