Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2378 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6762. Min Range: -8.6762
Max Act: 8.6762. Min Act: -0.1700
Data Index: 5369030 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6762. Min Range: -8.6762
Max Act: 8.6137. Min Act: -0.1700
Data Index: 2815237 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6762. Min Range: -8.6762
Max Act: 8.5512. Min Act: -0.1700
Data Index: 2235998 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6762. Min Range: -8.6762
Max Act: 8.3637. Min Act: -0.1700
Data Index: 589307 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6762. Min Range: -8.6762
Max Act: 8.3637. Min Act: -0.1700
Data Index: 3900573 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6762. Min Range: -8.6762
Max Act: 8.3012. Min Act: -0.1700
Data Index: 8003507 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6762. Min Range: -8.6762
Max Act: 8.2387. Min Act: -0.1700
Data Index: 2118566 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6762. Min Range: -8.6762
Max Act: 8.2387. Min Act: -0.1700
Data Index: 7761679 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6762. Min Range: -8.6762
Max Act: 8.1762. Min Act: -0.1700
Data Index: 3313456 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6762. Min Range: -8.6762
Max Act: 8.1762. Min Act: -0.1700
Data Index: 5767627 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6762. Min Range: -8.6762
Max Act: 8.1762. Min Act: -0.1700
Data Index: 3864955 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6762. Min Range: -8.6762
Max Act: 8.1762. Min Act: -0.1700
Data Index: 653364 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6762. Min Range: -8.6762
Max Act: 8.1762. Min Act: -0.1700
Data Index: 3856298 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6762. Min Range: -8.6762
Max Act: 8.1762. Min Act: -0.1700
Data Index: 2820564 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6762. Min Range: -8.6762
Max Act: 8.1762. Min Act: -0.1700
Data Index: 2752617 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6762. Min Range: -8.6762
Max Act: 8.1137. Min Act: -0.1700
Data Index: 7529520 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6762. Min Range: -8.6762
Max Act: 8.1137. Min Act: -0.1700
Data Index: 667215 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6762. Min Range: -8.6762
Max Act: 8.1137. Min Act: -0.1700
Data Index: 7522649 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6762. Min Range: -8.6762
Max Act: 8.1137. Min Act: -0.1700
Data Index: 2987184 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6762. Min Range: -8.6762
Max Act: 8.1137. Min Act: -0.1700
Data Index: 4178679 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #19