Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3666 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.2751. Min Range: -4.2751
Max Act: 4.2751. Min Act: -0.1700
Data Index: 8211462 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2751. Min Range: -4.2751
Max Act: 4.2751. Min Act: -0.1700
Data Index: 466619 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2751. Min Range: -4.2751
Max Act: 4.2438. Min Act: -0.1700
Data Index: 7136509 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2751. Min Range: -4.2751
Max Act: 4.2438. Min Act: -0.1700
Data Index: 7407509 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2751. Min Range: -4.2751
Max Act: 4.2126. Min Act: -0.1700
Data Index: 7264986 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2751. Min Range: -4.2751
Max Act: 4.2126. Min Act: -0.1700
Data Index: 8630933 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2751. Min Range: -4.2751
Max Act: 4.2126. Min Act: -0.1700
Data Index: 6862264 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2751. Min Range: -4.2751
Max Act: 4.2126. Min Act: -0.1700
Data Index: 1410640 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2751. Min Range: -4.2751
Max Act: 4.2126. Min Act: -0.1700
Data Index: 1628290 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2751. Min Range: -4.2751
Max Act: 4.2126. Min Act: -0.1700
Data Index: 7009724 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2751. Min Range: -4.2751
Max Act: 4.1813. Min Act: -0.1700
Data Index: 8822206 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2751. Min Range: -4.2751
Max Act: 4.1813. Min Act: -0.1700
Data Index: 993620 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2751. Min Range: -4.2751
Max Act: 4.1813. Min Act: -0.1700
Data Index: 3614813 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2751. Min Range: -4.2751
Max Act: 4.1500. Min Act: -0.1700
Data Index: 6716489 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2751. Min Range: -4.2751
Max Act: 4.1500. Min Act: -0.1700
Data Index: 3307400 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2751. Min Range: -4.2751
Max Act: 4.1500. Min Act: -0.1700
Data Index: 3307401 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2751. Min Range: -4.2751
Max Act: 4.1500. Min Act: -0.1700
Data Index: 5638790 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2751. Min Range: -4.2751
Max Act: 4.1500. Min Act: -0.1700
Data Index: 5446721 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2751. Min Range: -4.2751
Max Act: 4.1500. Min Act: -0.1700
Data Index: 893708 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2751. Min Range: -4.2751
Max Act: 4.1813. Min Act: -0.1700
Data Index: 7458713 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #19