Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3117 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7939. Min Range: -6.7939
Max Act: 6.7939. Min Act: -0.1700
Data Index: 6266502 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7939. Min Range: -6.7939
Max Act: 6.7939. Min Act: -0.1700
Data Index: 2928177 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7939. Min Range: -6.7939
Max Act: 6.6064. Min Act: -0.1700
Data Index: 4392197 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7939. Min Range: -6.7939
Max Act: 6.5439. Min Act: -0.1700
Data Index: 8731215 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7939. Min Range: -6.7939
Max Act: 6.4814. Min Act: -0.1700
Data Index: 1300791 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7939. Min Range: -6.7939
Max Act: 6.4189. Min Act: -0.1700
Data Index: 2221328 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7939. Min Range: -6.7939
Max Act: 6.3876. Min Act: -0.1700
Data Index: 647408 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7939. Min Range: -6.7939
Max Act: 6.3876. Min Act: -0.1700
Data Index: 4630742 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7939. Min Range: -6.7939
Max Act: 6.3876. Min Act: -0.1700
Data Index: 1043320 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7939. Min Range: -6.7939
Max Act: 6.3564. Min Act: -0.1700
Data Index: 6400470 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7939. Min Range: -6.7939
Max Act: 6.3251. Min Act: -0.1700
Data Index: 554813 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7939. Min Range: -6.7939
Max Act: 6.3251. Min Act: -0.1700
Data Index: 8385271 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7939. Min Range: -6.7939
Max Act: 6.3251. Min Act: -0.1700
Data Index: 5412523 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7939. Min Range: -6.7939
Max Act: 6.3251. Min Act: -0.1700
Data Index: 1876256 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7939. Min Range: -6.7939
Max Act: 6.2939. Min Act: -0.1700
Data Index: 5240868 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7939. Min Range: -6.7939
Max Act: 6.2939. Min Act: -0.1700
Data Index: 3871343 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7939. Min Range: -6.7939
Max Act: 6.2939. Min Act: -0.1700
Data Index: 3827683 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7939. Min Range: -6.7939
Max Act: 6.2939. Min Act: -0.1700
Data Index: 2813249 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7939. Min Range: -6.7939
Max Act: 6.2939. Min Act: -0.1700
Data Index: 4527460 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7939. Min Range: -6.7939
Max Act: 6.2939. Min Act: -0.1700
Data Index: 2711142 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #19