Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3543 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8687. Min Range: -5.8687
Max Act: 5.8687. Min Act: -0.1700
Data Index: 3050573 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8687. Min Range: -5.8687
Max Act: 5.8687. Min Act: -0.1700
Data Index: 7859308 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8687. Min Range: -5.8687
Max Act: 5.8687. Min Act: -0.1700
Data Index: 2589827 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8687. Min Range: -5.8687
Max Act: 5.8062. Min Act: -0.1700
Data Index: 2330455 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8687. Min Range: -5.8687
Max Act: 5.7749. Min Act: -0.1700
Data Index: 7979960 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8687. Min Range: -5.8687
Max Act: 5.7749. Min Act: -0.1700
Data Index: 6918847 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8687. Min Range: -5.8687
Max Act: 5.7437. Min Act: -0.1700
Data Index: 3944903 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8687. Min Range: -5.8687
Max Act: 5.7124. Min Act: -0.1700
Data Index: 6664232 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8687. Min Range: -5.8687
Max Act: 5.6812. Min Act: -0.1700
Data Index: 3285551 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8687. Min Range: -5.8687
Max Act: 5.6187. Min Act: -0.1700
Data Index: 7216553 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8687. Min Range: -5.8687
Max Act: 5.6499. Min Act: -0.1700
Data Index: 4469709 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8687. Min Range: -5.8687
Max Act: 5.6499. Min Act: -0.1700
Data Index: 7065694 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8687. Min Range: -5.8687
Max Act: 5.6499. Min Act: -0.1700
Data Index: 5661403 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8687. Min Range: -5.8687
Max Act: 5.6187. Min Act: -0.1700
Data Index: 2012749 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8687. Min Range: -5.8687
Max Act: 5.5874. Min Act: -0.1700
Data Index: 8283340 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8687. Min Range: -5.8687
Max Act: 5.5562. Min Act: -0.1700
Data Index: 3046922 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8687. Min Range: -5.8687
Max Act: 5.5562. Min Act: -0.1700
Data Index: 8612154 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8687. Min Range: -5.8687
Max Act: 5.5249. Min Act: -0.1700
Data Index: 2011281 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8687. Min Range: -5.8687
Max Act: 5.5562. Min Act: -0.1700
Data Index: 1517879 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8687. Min Range: -5.8687
Max Act: 5.5249. Min Act: -0.1700
Data Index: 422485 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #19