Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3944 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8057. Min Range: -6.8057
Max Act: 6.8057. Min Act: -0.1700
Data Index: 8314960 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8057. Min Range: -6.8057
Max Act: 6.7432. Min Act: -0.1700
Data Index: 4190673 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8057. Min Range: -6.8057
Max Act: 6.7120. Min Act: -0.1700
Data Index: 152668 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8057. Min Range: -6.8057
Max Act: 6.5557. Min Act: -0.1700
Data Index: 4399890 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8057. Min Range: -6.8057
Max Act: 6.5870. Min Act: -0.1700
Data Index: 4246971 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8057. Min Range: -6.8057
Max Act: 6.4932. Min Act: -0.1700
Data Index: 3131906 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8057. Min Range: -6.8057
Max Act: 6.4932. Min Act: -0.1700
Data Index: 4013221 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8057. Min Range: -6.8057
Max Act: 6.4620. Min Act: -0.1700
Data Index: 2681862 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8057. Min Range: -6.8057
Max Act: 6.4307. Min Act: -0.1700
Data Index: 8609299 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8057. Min Range: -6.8057
Max Act: 6.4307. Min Act: -0.1700
Data Index: 5721908 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8057. Min Range: -6.8057
Max Act: 6.4307. Min Act: -0.1700
Data Index: 8462602 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8057. Min Range: -6.8057
Max Act: 6.3682. Min Act: -0.1700
Data Index: 8158893 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8057. Min Range: -6.8057
Max Act: 6.3682. Min Act: -0.1700
Data Index: 4797882 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8057. Min Range: -6.8057
Max Act: 6.3057. Min Act: -0.1700
Data Index: 6514752 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8057. Min Range: -6.8057
Max Act: 6.3057. Min Act: -0.1700
Data Index: 5820253 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8057. Min Range: -6.8057
Max Act: 6.3057. Min Act: -0.1700
Data Index: 2745242 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8057. Min Range: -6.8057
Max Act: 6.3057. Min Act: -0.1700
Data Index: 1957989 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8057. Min Range: -6.8057
Max Act: 6.3370. Min Act: -0.1700
Data Index: 7134867 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8057. Min Range: -6.8057
Max Act: 6.2745. Min Act: -0.1700
Data Index: 8503426 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8057. Min Range: -6.8057
Max Act: 6.3057. Min Act: -0.1700
Data Index: 3580715 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #19