Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 476 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.1849. Min Range: -10.1849
Max Act: 10.1849. Min Act: -0.1700
Data Index: 8115851 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.1849. Min Range: -10.1849
Max Act: 10.1224. Min Act: -0.1700
Data Index: 6988787 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.1849. Min Range: -10.1849
Max Act: 10.0599. Min Act: -0.1700
Data Index: 6100789 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.1849. Min Range: -10.1849
Max Act: 10.0599. Min Act: -0.1700
Data Index: 3832594 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.1849. Min Range: -10.1849
Max Act: 10.0599. Min Act: -0.1700
Data Index: 1645857 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.1849. Min Range: -10.1849
Max Act: 9.9974. Min Act: -0.1700
Data Index: 1281852 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.1849. Min Range: -10.1849
Max Act: 9.8724. Min Act: -0.1700
Data Index: 8581825 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.1849. Min Range: -10.1849
Max Act: 9.8099. Min Act: -0.1700
Data Index: 8583492 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.1849. Min Range: -10.1849
Max Act: 9.8099. Min Act: -0.1700
Data Index: 6988786 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.1849. Min Range: -10.1849
Max Act: 9.8099. Min Act: -0.1700
Data Index: 8495907 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.1849. Min Range: -10.1849
Max Act: 9.8099. Min Act: -0.1700
Data Index: 6150477 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.1849. Min Range: -10.1849
Max Act: 9.8099. Min Act: -0.1700
Data Index: 4076774 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.1849. Min Range: -10.1849
Max Act: 9.8099. Min Act: -0.1700
Data Index: 6150467 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.1849. Min Range: -10.1849
Max Act: 9.7474. Min Act: -0.1700
Data Index: 4076586 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.1849. Min Range: -10.1849
Max Act: 9.7474. Min Act: -0.1700
Data Index: 1281851 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.1849. Min Range: -10.1849
Max Act: 9.6224. Min Act: -0.1700
Data Index: 4683554 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.1849. Min Range: -10.1849
Max Act: 9.6849. Min Act: -0.1700
Data Index: 7568618 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.1849. Min Range: -10.1849
Max Act: 9.6224. Min Act: -0.1700
Data Index: 294501 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.1849. Min Range: -10.1849
Max Act: 9.6224. Min Act: -0.1700
Data Index: 7979471 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.1849. Min Range: -10.1849
Max Act: 9.6224. Min Act: -0.1700
Data Index: 7934510 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #19