Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3591 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4766. Min Range: -7.4766
Max Act: 7.4766. Min Act: -0.1700
Data Index: 7603667 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4766. Min Range: -7.4766
Max Act: 7.4141. Min Act: -0.1700
Data Index: 3107859 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4766. Min Range: -7.4766
Max Act: 7.3203. Min Act: -0.1700
Data Index: 2651521 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4766. Min Range: -7.4766
Max Act: 7.1016. Min Act: -0.1700
Data Index: 1131894 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4766. Min Range: -7.4766
Max Act: 6.9141. Min Act: -0.1700
Data Index: 7052264 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4766. Min Range: -7.4766
Max Act: 6.9141. Min Act: -0.1700
Data Index: 3345119 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4766. Min Range: -7.4766
Max Act: 6.9141. Min Act: -0.1700
Data Index: 7013072 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4766. Min Range: -7.4766
Max Act: 6.8516. Min Act: -0.1700
Data Index: 4535161 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4766. Min Range: -7.4766
Max Act: 6.8516. Min Act: -0.1700
Data Index: 3161211 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4766. Min Range: -7.4766
Max Act: 6.8516. Min Act: -0.1700
Data Index: 5891896 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4766. Min Range: -7.4766
Max Act: 6.8203. Min Act: -0.1700
Data Index: 1131897 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4766. Min Range: -7.4766
Max Act: 6.7891. Min Act: -0.1700
Data Index: 7529480 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4766. Min Range: -7.4766
Max Act: 6.7891. Min Act: -0.1700
Data Index: 680018 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4766. Min Range: -7.4766
Max Act: 6.7891. Min Act: -0.1700
Data Index: 4407298 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4766. Min Range: -7.4766
Max Act: 6.7578. Min Act: -0.1700
Data Index: 2810433 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4766. Min Range: -7.4766
Max Act: 6.7266. Min Act: -0.1700
Data Index: 7461817 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4766. Min Range: -7.4766
Max Act: 6.6641. Min Act: -0.1700
Data Index: 561009 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4766. Min Range: -7.4766
Max Act: 6.6641. Min Act: -0.1700
Data Index: 7410876 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4766. Min Range: -7.4766
Max Act: 6.6641. Min Act: -0.1700
Data Index: 3497839 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4766. Min Range: -7.4766
Max Act: 6.6641. Min Act: -0.1700
Data Index: 4797630 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #19