Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6098 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1781. Min Range: -8.1781
Max Act: 8.1781. Min Act: -0.1700
Data Index: 2729837 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1781. Min Range: -8.1781
Max Act: 8.1156. Min Act: -0.1700
Data Index: 470817 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1781. Min Range: -8.1781
Max Act: 7.8343. Min Act: -0.1700
Data Index: 4528005 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1781. Min Range: -8.1781
Max Act: 7.8343. Min Act: -0.1700
Data Index: 6658448 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1781. Min Range: -8.1781
Max Act: 7.7406. Min Act: -0.1700
Data Index: 5629057 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1781. Min Range: -8.1781
Max Act: 7.7093. Min Act: -0.1700
Data Index: 652175 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1781. Min Range: -8.1781
Max Act: 7.6468. Min Act: -0.1700
Data Index: 197286 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1781. Min Range: -8.1781
Max Act: 7.6468. Min Act: -0.1700
Data Index: 4617387 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1781. Min Range: -8.1781
Max Act: 7.6156. Min Act: -0.1700
Data Index: 6978543 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1781. Min Range: -8.1781
Max Act: 7.5531. Min Act: -0.1700
Data Index: 6926801 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1781. Min Range: -8.1781
Max Act: 7.5531. Min Act: -0.1700
Data Index: 7385801 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1781. Min Range: -8.1781
Max Act: 7.5218. Min Act: -0.1700
Data Index: 3459346 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1781. Min Range: -8.1781
Max Act: 7.5218. Min Act: -0.1700
Data Index: 2039008 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1781. Min Range: -8.1781
Max Act: 7.4906. Min Act: -0.1700
Data Index: 5251893 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1781. Min Range: -8.1781
Max Act: 7.5218. Min Act: -0.1700
Data Index: 2768829 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1781. Min Range: -8.1781
Max Act: 7.4593. Min Act: -0.1700
Data Index: 4036671 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1781. Min Range: -8.1781
Max Act: 7.4906. Min Act: -0.1700
Data Index: 4576421 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1781. Min Range: -8.1781
Max Act: 7.4281. Min Act: -0.1700
Data Index: 1676698 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1781. Min Range: -8.1781
Max Act: 7.4281. Min Act: -0.1700
Data Index: 832884 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1781. Min Range: -8.1781
Max Act: 7.4281. Min Act: -0.1700
Data Index: 3735637 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #19