Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2661 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0355. Min Range: -8.0355
Max Act: 8.0355. Min Act: -0.1700
Data Index: 2233536 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0355. Min Range: -8.0355
Max Act: 7.7230. Min Act: -0.1700
Data Index: 5793853 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0355. Min Range: -8.0355
Max Act: 7.7230. Min Act: -0.1700
Data Index: 6314237 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0355. Min Range: -8.0355
Max Act: 7.7230. Min Act: -0.1700
Data Index: 4982817 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0355. Min Range: -8.0355
Max Act: 7.6605. Min Act: -0.1700
Data Index: 8330018 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0355. Min Range: -8.0355
Max Act: 7.6605. Min Act: -0.1700
Data Index: 4375156 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0355. Min Range: -8.0355
Max Act: 7.5355. Min Act: -0.1700
Data Index: 8522679 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0355. Min Range: -8.0355
Max Act: 7.5355. Min Act: -0.1700
Data Index: 2014839 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0355. Min Range: -8.0355
Max Act: 7.5355. Min Act: -0.1700
Data Index: 4210574 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0355. Min Range: -8.0355
Max Act: 7.5355. Min Act: -0.1700
Data Index: 7168269 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0355. Min Range: -8.0355
Max Act: 7.5355. Min Act: -0.1700
Data Index: 2133977 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0355. Min Range: -8.0355
Max Act: 7.5355. Min Act: -0.1700
Data Index: 8782590 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0355. Min Range: -8.0355
Max Act: 7.4730. Min Act: -0.1700
Data Index: 660433 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0355. Min Range: -8.0355
Max Act: 7.4730. Min Act: -0.1700
Data Index: 6204480 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0355. Min Range: -8.0355
Max Act: 7.4730. Min Act: -0.1700
Data Index: 4124874 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0355. Min Range: -8.0355
Max Act: 7.4730. Min Act: -0.1700
Data Index: 5162042 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0355. Min Range: -8.0355
Max Act: 7.4417. Min Act: -0.1700
Data Index: 6526536 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0355. Min Range: -8.0355
Max Act: 7.4417. Min Act: -0.1700
Data Index: 2961678 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0355. Min Range: -8.0355
Max Act: 7.4105. Min Act: -0.1700
Data Index: 8476100 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0355. Min Range: -8.0355
Max Act: 7.4417. Min Act: -0.1700
Data Index: 3766800 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #19