Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3769 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5453. Min Range: -6.5453
Max Act: 6.5453. Min Act: -0.1700
Data Index: 8483378 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5453. Min Range: -6.5453
Max Act: 6.3578. Min Act: -0.1700
Data Index: 6191592 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5453. Min Range: -6.5453
Max Act: 6.3578. Min Act: -0.1700
Data Index: 113641 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5453. Min Range: -6.5453
Max Act: 6.3578. Min Act: -0.1700
Data Index: 8027373 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5453. Min Range: -6.5453
Max Act: 6.2641. Min Act: -0.1700
Data Index: 3598733 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5453. Min Range: -6.5453
Max Act: 6.2016. Min Act: -0.1700
Data Index: 8239570 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5453. Min Range: -6.5453
Max Act: 6.1391. Min Act: -0.1700
Data Index: 2400161 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5453. Min Range: -6.5453
Max Act: 6.1391. Min Act: -0.1700
Data Index: 4979605 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5453. Min Range: -6.5453
Max Act: 6.0766. Min Act: -0.1700
Data Index: 3008725 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5453. Min Range: -6.5453
Max Act: 6.0766. Min Act: -0.1700
Data Index: 5585143 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5453. Min Range: -6.5453
Max Act: 6.0766. Min Act: -0.1700
Data Index: 2912747 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5453. Min Range: -6.5453
Max Act: 6.0453. Min Act: -0.1700
Data Index: 8423834 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5453. Min Range: -6.5453
Max Act: 6.0141. Min Act: -0.1700
Data Index: 1921810 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5453. Min Range: -6.5453
Max Act: 6.0141. Min Act: -0.1700
Data Index: 3000760 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5453. Min Range: -6.5453
Max Act: 6.0141. Min Act: -0.1700
Data Index: 5972762 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5453. Min Range: -6.5453
Max Act: 5.9828. Min Act: -0.1700
Data Index: 3025949 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5453. Min Range: -6.5453
Max Act: 6.0141. Min Act: -0.1700
Data Index: 6597434 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5453. Min Range: -6.5453
Max Act: 5.9828. Min Act: -0.1700
Data Index: 2887776 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5453. Min Range: -6.5453
Max Act: 5.9516. Min Act: -0.1700
Data Index: 5731638 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5453. Min Range: -6.5453
Max Act: 5.9828. Min Act: -0.1700
Data Index: 8086770 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #19