Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2254 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0634. Min Range: -6.0634
Max Act: 6.0634. Min Act: -0.1700
Data Index: 2483627 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0634. Min Range: -6.0634
Max Act: 5.9697. Min Act: -0.1700
Data Index: 3685965 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0634. Min Range: -6.0634
Max Act: 5.9697. Min Act: -0.1700
Data Index: 1200599 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0634. Min Range: -6.0634
Max Act: 5.9384. Min Act: -0.1700
Data Index: 5639735 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0634. Min Range: -6.0634
Max Act: 5.9384. Min Act: -0.1700
Data Index: 555118 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0634. Min Range: -6.0634
Max Act: 5.9384. Min Act: -0.1700
Data Index: 4066568 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0634. Min Range: -6.0634
Max Act: 5.9384. Min Act: -0.1700
Data Index: 2127349 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0634. Min Range: -6.0634
Max Act: 5.9072. Min Act: -0.1700
Data Index: 2378509 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0634. Min Range: -6.0634
Max Act: 5.8759. Min Act: -0.1700
Data Index: 3410278 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0634. Min Range: -6.0634
Max Act: 5.8759. Min Act: -0.1700
Data Index: 6008733 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0634. Min Range: -6.0634
Max Act: 5.8759. Min Act: -0.1700
Data Index: 1583631 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0634. Min Range: -6.0634
Max Act: 5.8447. Min Act: -0.1700
Data Index: 7417900 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0634. Min Range: -6.0634
Max Act: 5.8134. Min Act: -0.1700
Data Index: 1597055 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0634. Min Range: -6.0634
Max Act: 5.8134. Min Act: -0.1700
Data Index: 2653911 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0634. Min Range: -6.0634
Max Act: 5.7822. Min Act: -0.1700
Data Index: 8653162 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0634. Min Range: -6.0634
Max Act: 5.7822. Min Act: -0.1700
Data Index: 1640692 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0634. Min Range: -6.0634
Max Act: 5.7822. Min Act: -0.1700
Data Index: 3723169 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0634. Min Range: -6.0634
Max Act: 5.7822. Min Act: -0.1700
Data Index: 461073 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0634. Min Range: -6.0634
Max Act: 5.7822. Min Act: -0.1700
Data Index: 504014 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0634. Min Range: -6.0634
Max Act: 5.7822. Min Act: -0.1700
Data Index: 5598868 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #19