Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2783 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2878. Min Range: -6.2878
Max Act: 6.2878. Min Act: -0.1700
Data Index: 5725954 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2878. Min Range: -6.2878
Max Act: 6.1315. Min Act: -0.1700
Data Index: 7912582 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2878. Min Range: -6.2878
Max Act: 5.9440. Min Act: -0.1700
Data Index: 7609772 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2878. Min Range: -6.2878
Max Act: 5.9440. Min Act: -0.1700
Data Index: 1358700 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2878. Min Range: -6.2878
Max Act: 5.8815. Min Act: -0.1700
Data Index: 5003193 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2878. Min Range: -6.2878
Max Act: 5.8503. Min Act: -0.1700
Data Index: 749058 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2878. Min Range: -6.2878
Max Act: 5.8190. Min Act: -0.1700
Data Index: 2336232 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2878. Min Range: -6.2878
Max Act: 5.7253. Min Act: -0.1700
Data Index: 6107755 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2878. Min Range: -6.2878
Max Act: 5.7565. Min Act: -0.1700
Data Index: 2467818 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2878. Min Range: -6.2878
Max Act: 5.7253. Min Act: -0.1700
Data Index: 3610600 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2878. Min Range: -6.2878
Max Act: 5.7253. Min Act: -0.1700
Data Index: 6181876 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2878. Min Range: -6.2878
Max Act: 5.6940. Min Act: -0.1700
Data Index: 1480136 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2878. Min Range: -6.2878
Max Act: 5.6940. Min Act: -0.1700
Data Index: 6407049 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2878. Min Range: -6.2878
Max Act: 5.6940. Min Act: -0.1700
Data Index: 8609869 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2878. Min Range: -6.2878
Max Act: 5.6940. Min Act: -0.1700
Data Index: 2855758 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2878. Min Range: -6.2878
Max Act: 5.6628. Min Act: -0.1700
Data Index: 7983072 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2878. Min Range: -6.2878
Max Act: 5.6628. Min Act: -0.1700
Data Index: 2393536 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2878. Min Range: -6.2878
Max Act: 5.6628. Min Act: -0.1700
Data Index: 113121 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2878. Min Range: -6.2878
Max Act: 5.6628. Min Act: -0.1700
Data Index: 6826059 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2878. Min Range: -6.2878
Max Act: 5.6315. Min Act: -0.1700
Data Index: 1543286 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #19