Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4554 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4127. Min Range: -7.4127
Max Act: 7.4127. Min Act: -0.1700
Data Index: 135061 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4127. Min Range: -7.4127
Max Act: 7.2564. Min Act: -0.1700
Data Index: 3739603 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4127. Min Range: -7.4127
Max Act: 7.1627. Min Act: -0.1700
Data Index: 7100055 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4127. Min Range: -7.4127
Max Act: 7.1002. Min Act: -0.1700
Data Index: 2718005 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4127. Min Range: -7.4127
Max Act: 7.1002. Min Act: -0.1700
Data Index: 6915443 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4127. Min Range: -7.4127
Max Act: 7.0689. Min Act: -0.1700
Data Index: 4256598 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4127. Min Range: -7.4127
Max Act: 7.1627. Min Act: -0.1700
Data Index: 2901828 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4127. Min Range: -7.4127
Max Act: 7.0689. Min Act: -0.1700
Data Index: 4486303 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4127. Min Range: -7.4127
Max Act: 7.0689. Min Act: -0.1700
Data Index: 6999297 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4127. Min Range: -7.4127
Max Act: 7.0689. Min Act: -0.1700
Data Index: 290738 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4127. Min Range: -7.4127
Max Act: 7.1002. Min Act: -0.1700
Data Index: 6167091 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4127. Min Range: -7.4127
Max Act: 7.0377. Min Act: -0.1700
Data Index: 4946182 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4127. Min Range: -7.4127
Max Act: 7.0377. Min Act: -0.1700
Data Index: 2092370 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4127. Min Range: -7.4127
Max Act: 7.0064. Min Act: -0.1700
Data Index: 8738142 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4127. Min Range: -7.4127
Max Act: 7.0064. Min Act: -0.1700
Data Index: 5243842 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4127. Min Range: -7.4127
Max Act: 7.0064. Min Act: -0.1700
Data Index: 8353103 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4127. Min Range: -7.4127
Max Act: 7.0064. Min Act: -0.1700
Data Index: 6841234 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4127. Min Range: -7.4127
Max Act: 6.9439. Min Act: -0.1700
Data Index: 8201713 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4127. Min Range: -7.4127
Max Act: 6.9752. Min Act: -0.1700
Data Index: 6423709 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4127. Min Range: -7.4127
Max Act: 6.9752. Min Act: -0.1700
Data Index: 4649147 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #19