Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4476 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 0.8793. Min Range: -0.8793
Max Act: 0.8793. Min Act: -0.1700
Data Index: 169157 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.8793. Min Range: -0.8793
Max Act: 0.8793. Min Act: -0.1700
Data Index: 1609536 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.8793. Min Range: -0.8793
Max Act: 0.8793. Min Act: -0.1700
Data Index: 1708811 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.8793. Min Range: -0.8793
Max Act: 0.8622. Min Act: -0.1700
Data Index: 8651914 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.8793. Min Range: -0.8793
Max Act: 0.8368. Min Act: -0.1700
Data Index: 5243505 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.8793. Min Range: -0.8793
Max Act: 0.8284. Min Act: -0.1700
Data Index: 3393657 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.8793. Min Range: -0.8793
Max Act: 0.8368. Min Act: -0.1700
Data Index: 1500655 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.8793. Min Range: -0.8793
Max Act: 0.8199. Min Act: -0.1700
Data Index: 7844167 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.8793. Min Range: -0.8793
Max Act: 0.8199. Min Act: -0.1700
Data Index: 6508773 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.8793. Min Range: -0.8793
Max Act: 0.8115. Min Act: -0.1700
Data Index: 5102281 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.8793. Min Range: -0.8793
Max Act: 0.8115. Min Act: -0.1700
Data Index: 3225055 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.8793. Min Range: -0.8793
Max Act: 0.8115. Min Act: -0.1700
Data Index: 5420963 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.8793. Min Range: -0.8793
Max Act: 0.7947. Min Act: -0.1700
Data Index: 1014594 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.8793. Min Range: -0.8793
Max Act: 0.7947. Min Act: -0.1700
Data Index: 3608830 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.8793. Min Range: -0.8793
Max Act: 0.8031. Min Act: -0.1700
Data Index: 405841 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.8793. Min Range: -0.8793
Max Act: 0.7947. Min Act: -0.1700
Data Index: 7471200 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.8793. Min Range: -0.8793
Max Act: 0.7947. Min Act: -0.1700
Data Index: 4926147 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.8793. Min Range: -0.8793
Max Act: 0.7947. Min Act: -0.1700
Data Index: 5304011 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.8793. Min Range: -0.8793
Max Act: 0.7947. Min Act: -0.1700
Data Index: 7947830 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.8793. Min Range: -0.8793
Max Act: 0.7864. Min Act: -0.1700
Data Index: 717716 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #19