Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2720 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3496. Min Range: -7.3496
Max Act: 7.3496. Min Act: -0.1700
Data Index: 2105000 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3496. Min Range: -7.3496
Max Act: 6.9433. Min Act: -0.1700
Data Index: 3700851 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3496. Min Range: -7.3496
Max Act: 6.8808. Min Act: -0.1700
Data Index: 1972900 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3496. Min Range: -7.3496
Max Act: 6.8496. Min Act: -0.1700
Data Index: 711542 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3496. Min Range: -7.3496
Max Act: 6.7871. Min Act: -0.1700
Data Index: 2676505 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3496. Min Range: -7.3496
Max Act: 6.7558. Min Act: -0.1700
Data Index: 3738773 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3496. Min Range: -7.3496
Max Act: 6.7246. Min Act: -0.1700
Data Index: 1542298 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3496. Min Range: -7.3496
Max Act: 6.7246. Min Act: -0.1700
Data Index: 4435941 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3496. Min Range: -7.3496
Max Act: 6.6621. Min Act: -0.1700
Data Index: 5449861 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3496. Min Range: -7.3496
Max Act: 6.6933. Min Act: -0.1700
Data Index: 1270883 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3496. Min Range: -7.3496
Max Act: 6.6621. Min Act: -0.1700
Data Index: 10678 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3496. Min Range: -7.3496
Max Act: 6.6308. Min Act: -0.1700
Data Index: 2965260 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3496. Min Range: -7.3496
Max Act: 6.5996. Min Act: -0.1700
Data Index: 4435940 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3496. Min Range: -7.3496
Max Act: 6.5996. Min Act: -0.1700
Data Index: 4895490 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3496. Min Range: -7.3496
Max Act: 6.6308. Min Act: -0.1700
Data Index: 3805004 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3496. Min Range: -7.3496
Max Act: 6.5683. Min Act: -0.1700
Data Index: 1270884 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3496. Min Range: -7.3496
Max Act: 6.5683. Min Act: -0.1700
Data Index: 2051025 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3496. Min Range: -7.3496
Max Act: 6.5683. Min Act: -0.1700
Data Index: 5603716 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3496. Min Range: -7.3496
Max Act: 6.5058. Min Act: -0.1700
Data Index: 3127197 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3496. Min Range: -7.3496
Max Act: 6.5058. Min Act: -0.1700
Data Index: 10680 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #19