Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 101 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.5090. Min Range: -3.5090
Max Act: 3.5090. Min Act: -0.1700
Data Index: 3018585 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5090. Min Range: -3.5090
Max Act: 3.5090. Min Act: -0.1700
Data Index: 3236885 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5090. Min Range: -3.5090
Max Act: 3.5090. Min Act: -0.1700
Data Index: 1479112 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5090. Min Range: -3.5090
Max Act: 3.4777. Min Act: -0.1700
Data Index: 3734887 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5090. Min Range: -3.5090
Max Act: 3.4777. Min Act: -0.1700
Data Index: 8485611 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5090. Min Range: -3.5090
Max Act: 3.4777. Min Act: -0.1700
Data Index: 8791899 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5090. Min Range: -3.5090
Max Act: 3.4463. Min Act: -0.1700
Data Index: 2321137 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5090. Min Range: -3.5090
Max Act: 3.4463. Min Act: -0.1699
Data Index: 3421629 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5090. Min Range: -3.5090
Max Act: 3.4150. Min Act: -0.1700
Data Index: 6465136 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5090. Min Range: -3.5090
Max Act: 3.4150. Min Act: -0.1700
Data Index: 331992 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5090. Min Range: -3.5090
Max Act: 3.3836. Min Act: -0.1700
Data Index: 8410729 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5090. Min Range: -3.5090
Max Act: 3.4150. Min Act: -0.1700
Data Index: 7465861 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5090. Min Range: -3.5090
Max Act: 3.4463. Min Act: -0.1700
Data Index: 6557664 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5090. Min Range: -3.5090
Max Act: 3.3836. Min Act: -0.1700
Data Index: 5516231 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5090. Min Range: -3.5090
Max Act: 3.4150. Min Act: -0.1700
Data Index: 4807843 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5090. Min Range: -3.5090
Max Act: 3.4150. Min Act: -0.1700
Data Index: 1083920 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5090. Min Range: -3.5090
Max Act: 3.4150. Min Act: -0.1700
Data Index: 2797581 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5090. Min Range: -3.5090
Max Act: 3.3836. Min Act: -0.1700
Data Index: 5119233 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5090. Min Range: -3.5090
Max Act: 3.3836. Min Act: -0.1700
Data Index: 5845052 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5090. Min Range: -3.5090
Max Act: 3.3836. Min Act: -0.1700
Data Index: 2147292 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #19