Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3055 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3984. Min Range: -8.3984
Max Act: 8.3984. Min Act: -0.1700
Data Index: 1979825 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3984. Min Range: -8.3984
Max Act: 8.0859. Min Act: -0.1700
Data Index: 5051641 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3984. Min Range: -8.3984
Max Act: 7.8984. Min Act: -0.1700
Data Index: 6188448 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3984. Min Range: -8.3984
Max Act: 7.8984. Min Act: -0.1700
Data Index: 6737886 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3984. Min Range: -8.3984
Max Act: 7.8984. Min Act: -0.1700
Data Index: 5394659 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3984. Min Range: -8.3984
Max Act: 7.8984. Min Act: -0.1700
Data Index: 2772002 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3984. Min Range: -8.3984
Max Act: 7.8359. Min Act: -0.1700
Data Index: 4393697 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3984. Min Range: -8.3984
Max Act: 7.8359. Min Act: -0.1700
Data Index: 1478019 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3984. Min Range: -8.3984
Max Act: 7.7734. Min Act: -0.1700
Data Index: 486027 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3984. Min Range: -8.3984
Max Act: 7.7734. Min Act: -0.1700
Data Index: 5479496 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3984. Min Range: -8.3984
Max Act: 7.7734. Min Act: -0.1700
Data Index: 4402759 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3984. Min Range: -8.3984
Max Act: 7.7734. Min Act: -0.1700
Data Index: 91331 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3984. Min Range: -8.3984
Max Act: 7.7734. Min Act: -0.1700
Data Index: 7570382 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3984. Min Range: -8.3984
Max Act: 7.7734. Min Act: -0.1700
Data Index: 4648684 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3984. Min Range: -8.3984
Max Act: 7.7734. Min Act: -0.1700
Data Index: 277776 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3984. Min Range: -8.3984
Max Act: 7.7109. Min Act: -0.1700
Data Index: 1362370 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3984. Min Range: -8.3984
Max Act: 7.7109. Min Act: -0.1700
Data Index: 977397 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3984. Min Range: -8.3984
Max Act: 7.6484. Min Act: -0.1700
Data Index: 2939469 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3984. Min Range: -8.3984
Max Act: 7.6484. Min Act: -0.1700
Data Index: 1347990 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3984. Min Range: -8.3984
Max Act: 7.6484. Min Act: -0.1700
Data Index: 6099885 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #19