Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2944 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2516. Min Range: -6.2516
Max Act: 6.2516. Min Act: -0.1700
Data Index: 190061 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2516. Min Range: -6.2516
Max Act: 6.2204. Min Act: -0.1700
Data Index: 6373093 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2516. Min Range: -6.2516
Max Act: 6.1891. Min Act: -0.1700
Data Index: 725757 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2516. Min Range: -6.2516
Max Act: 6.1891. Min Act: -0.1700
Data Index: 2201732 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2516. Min Range: -6.2516
Max Act: 6.0641. Min Act: -0.1700
Data Index: 3307497 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2516. Min Range: -6.2516
Max Act: 6.0329. Min Act: -0.1700
Data Index: 1012333 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2516. Min Range: -6.2516
Max Act: 5.9704. Min Act: -0.1700
Data Index: 5241727 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2516. Min Range: -6.2516
Max Act: 5.9704. Min Act: -0.1700
Data Index: 5767759 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2516. Min Range: -6.2516
Max Act: 5.9391. Min Act: -0.1700
Data Index: 250499 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2516. Min Range: -6.2516
Max Act: 5.9391. Min Act: -0.1700
Data Index: 261765 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2516. Min Range: -6.2516
Max Act: 5.9079. Min Act: -0.1700
Data Index: 2905455 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2516. Min Range: -6.2516
Max Act: 5.9391. Min Act: -0.1700
Data Index: 4572352 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2516. Min Range: -6.2516
Max Act: 5.8766. Min Act: -0.1700
Data Index: 8504608 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2516. Min Range: -6.2516
Max Act: 5.8766. Min Act: -0.1700
Data Index: 106495 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2516. Min Range: -6.2516
Max Act: 5.8454. Min Act: -0.1700
Data Index: 5138641 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2516. Min Range: -6.2516
Max Act: 5.8766. Min Act: -0.1700
Data Index: 7500076 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2516. Min Range: -6.2516
Max Act: 5.8141. Min Act: -0.1700
Data Index: 8438240 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2516. Min Range: -6.2516
Max Act: 5.8141. Min Act: -0.1700
Data Index: 5714392 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2516. Min Range: -6.2516
Max Act: 5.8141. Min Act: -0.1700
Data Index: 950606 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2516. Min Range: -6.2516
Max Act: 5.7829. Min Act: -0.1700
Data Index: 6769660 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #19