Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 572 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7920. Min Range: -5.7920
Max Act: 5.7920. Min Act: -0.1700
Data Index: 874784 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7920. Min Range: -5.7920
Max Act: 5.7608. Min Act: -0.1700
Data Index: 6052323 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7920. Min Range: -5.7920
Max Act: 5.7608. Min Act: -0.1700
Data Index: 8583426 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7920. Min Range: -5.7920
Max Act: 5.7608. Min Act: -0.1700
Data Index: 6138793 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7920. Min Range: -5.7920
Max Act: 5.6983. Min Act: -0.1700
Data Index: 1810185 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7920. Min Range: -5.7920
Max Act: 5.6670. Min Act: -0.1700
Data Index: 7375876 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7920. Min Range: -5.7920
Max Act: 5.6670. Min Act: -0.1700
Data Index: 6898816 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7920. Min Range: -5.7920
Max Act: 5.6983. Min Act: -0.1700
Data Index: 4285708 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7920. Min Range: -5.7920
Max Act: 5.6045. Min Act: -0.1700
Data Index: 8075564 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7920. Min Range: -5.7920
Max Act: 5.5420. Min Act: -0.1700
Data Index: 518009 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7920. Min Range: -5.7920
Max Act: 5.5733. Min Act: -0.1700
Data Index: 1575851 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7920. Min Range: -5.7920
Max Act: 5.5420. Min Act: -0.1700
Data Index: 2697079 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7920. Min Range: -5.7920
Max Act: 5.5420. Min Act: -0.1700
Data Index: 6559581 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7920. Min Range: -5.7920
Max Act: 5.5108. Min Act: -0.1700
Data Index: 5033450 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7920. Min Range: -5.7920
Max Act: 5.5108. Min Act: -0.1700
Data Index: 8610886 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7920. Min Range: -5.7920
Max Act: 5.5108. Min Act: -0.1700
Data Index: 6559584 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7920. Min Range: -5.7920
Max Act: 5.5108. Min Act: -0.1700
Data Index: 6559583 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7920. Min Range: -5.7920
Max Act: 5.4795. Min Act: -0.1700
Data Index: 2264937 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7920. Min Range: -5.7920
Max Act: 5.5108. Min Act: -0.1700
Data Index: 5459736 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7920. Min Range: -5.7920
Max Act: 5.4483. Min Act: -0.1700
Data Index: 1806299 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #19