Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3572 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9859. Min Range: -5.9859
Max Act: 5.9859. Min Act: -0.1700
Data Index: 5860886 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9859. Min Range: -5.9859
Max Act: 5.8297. Min Act: -0.1700
Data Index: 686084 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9859. Min Range: -5.9859
Max Act: 5.7984. Min Act: -0.1700
Data Index: 5648293 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9859. Min Range: -5.9859
Max Act: 5.7672. Min Act: -0.1700
Data Index: 7274654 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9859. Min Range: -5.9859
Max Act: 5.7359. Min Act: -0.1700
Data Index: 4430478 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9859. Min Range: -5.9859
Max Act: 5.7359. Min Act: -0.1700
Data Index: 7231347 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9859. Min Range: -5.9859
Max Act: 5.7359. Min Act: -0.1700
Data Index: 5114673 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9859. Min Range: -5.9859
Max Act: 5.7047. Min Act: -0.1700
Data Index: 7456763 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9859. Min Range: -5.9859
Max Act: 5.7047. Min Act: -0.1700
Data Index: 4078107 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9859. Min Range: -5.9859
Max Act: 5.7359. Min Act: -0.1700
Data Index: 4236245 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9859. Min Range: -5.9859
Max Act: 5.7047. Min Act: -0.1700
Data Index: 5371350 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9859. Min Range: -5.9859
Max Act: 5.6734. Min Act: -0.1700
Data Index: 5758904 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9859. Min Range: -5.9859
Max Act: 5.6734. Min Act: -0.1700
Data Index: 6231308 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9859. Min Range: -5.9859
Max Act: 5.6422. Min Act: -0.1700
Data Index: 4411214 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9859. Min Range: -5.9859
Max Act: 5.6734. Min Act: -0.1700
Data Index: 400275 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9859. Min Range: -5.9859
Max Act: 5.6734. Min Act: -0.1700
Data Index: 1017362 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9859. Min Range: -5.9859
Max Act: 5.6422. Min Act: -0.1700
Data Index: 3850053 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9859. Min Range: -5.9859
Max Act: 5.6109. Min Act: -0.1700
Data Index: 7495743 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9859. Min Range: -5.9859
Max Act: 5.6109. Min Act: -0.1700
Data Index: 2314826 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9859. Min Range: -5.9859
Max Act: 5.6109. Min Act: -0.1700
Data Index: 6979906 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #19