Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5012 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6746. Min Range: -6.6746
Max Act: 6.6746. Min Act: -0.1700
Data Index: 2531552 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6746. Min Range: -6.6746
Max Act: 6.5808. Min Act: -0.1700
Data Index: 1751791 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6746. Min Range: -6.6746
Max Act: 6.5183. Min Act: -0.1700
Data Index: 3319046 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6746. Min Range: -6.6746
Max Act: 6.4558. Min Act: -0.1700
Data Index: 6229128 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6746. Min Range: -6.6746
Max Act: 6.4246. Min Act: -0.1700
Data Index: 8308348 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6746. Min Range: -6.6746
Max Act: 6.3933. Min Act: -0.1700
Data Index: 8784193 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6746. Min Range: -6.6746
Max Act: 6.4246. Min Act: -0.1700
Data Index: 4481854 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6746. Min Range: -6.6746
Max Act: 6.3933. Min Act: -0.1700
Data Index: 71014 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6746. Min Range: -6.6746
Max Act: 6.3621. Min Act: -0.1700
Data Index: 1314888 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6746. Min Range: -6.6746
Max Act: 6.3308. Min Act: -0.1700
Data Index: 6787717 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6746. Min Range: -6.6746
Max Act: 6.3308. Min Act: -0.1700
Data Index: 6140038 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6746. Min Range: -6.6746
Max Act: 6.2683. Min Act: -0.1700
Data Index: 5063528 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6746. Min Range: -6.6746
Max Act: 6.2683. Min Act: -0.1700
Data Index: 2684870 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6746. Min Range: -6.6746
Max Act: 6.2058. Min Act: -0.1700
Data Index: 4724869 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6746. Min Range: -6.6746
Max Act: 6.1433. Min Act: -0.1700
Data Index: 6496877 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6746. Min Range: -6.6746
Max Act: 6.2058. Min Act: -0.1700
Data Index: 5302480 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6746. Min Range: -6.6746
Max Act: 6.1433. Min Act: -0.1700
Data Index: 5687410 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6746. Min Range: -6.6746
Max Act: 6.1433. Min Act: -0.1700
Data Index: 7316933 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6746. Min Range: -6.6746
Max Act: 6.1433. Min Act: -0.1700
Data Index: 4540494 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6746. Min Range: -6.6746
Max Act: 6.1746. Min Act: -0.1700
Data Index: 321697 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #19