Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3066 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.6644. Min Range: -9.6644
Max Act: 9.6644. Min Act: -0.1700
Data Index: 5288921 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.6644. Min Range: -9.6644
Max Act: 9.6019. Min Act: -0.1700
Data Index: 3580058 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.6644. Min Range: -9.6644
Max Act: 9.1644. Min Act: -0.1700
Data Index: 13860 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.6644. Min Range: -9.6644
Max Act: 9.2269. Min Act: -0.1700
Data Index: 8709897 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.6644. Min Range: -9.6644
Max Act: 9.1019. Min Act: -0.1700
Data Index: 3500326 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.6644. Min Range: -9.6644
Max Act: 9.1019. Min Act: -0.1700
Data Index: 3982761 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.6644. Min Range: -9.6644
Max Act: 9.1019. Min Act: -0.1700
Data Index: 5288920 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.6644. Min Range: -9.6644
Max Act: 9.1019. Min Act: -0.1700
Data Index: 1902813 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.6644. Min Range: -9.6644
Max Act: 9.0394. Min Act: -0.1700
Data Index: 2335183 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.6644. Min Range: -9.6644
Max Act: 9.0394. Min Act: -0.1700
Data Index: 7377756 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.6644. Min Range: -9.6644
Max Act: 9.1019. Min Act: -0.1700
Data Index: 417469 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.6644. Min Range: -9.6644
Max Act: 9.0394. Min Act: -0.1700
Data Index: 5119894 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.6644. Min Range: -9.6644
Max Act: 8.9769. Min Act: -0.1700
Data Index: 8586244 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.6644. Min Range: -9.6644
Max Act: 8.9769. Min Act: -0.1700
Data Index: 3392682 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.6644. Min Range: -9.6644
Max Act: 8.9769. Min Act: -0.1700
Data Index: 4179503 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.6644. Min Range: -9.6644
Max Act: 8.9769. Min Act: -0.1700
Data Index: 1220082 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.6644. Min Range: -9.6644
Max Act: 8.9144. Min Act: -0.1700
Data Index: 242597 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.6644. Min Range: -9.6644
Max Act: 8.9144. Min Act: -0.1700
Data Index: 1234765 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.6644. Min Range: -9.6644
Max Act: 8.8519. Min Act: -0.1700
Data Index: 7660595 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.6644. Min Range: -9.6644
Max Act: 8.8519. Min Act: -0.1700
Data Index: 1579421 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #19