Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3580 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2701. Min Range: -5.2701
Max Act: 5.2701. Min Act: -0.1700
Data Index: 5001127 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2701. Min Range: -5.2701
Max Act: 5.1138. Min Act: -0.1700
Data Index: 6956015 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2701. Min Range: -5.2701
Max Act: 5.1451. Min Act: -0.1700
Data Index: 411218 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2701. Min Range: -5.2701
Max Act: 5.0826. Min Act: -0.1700
Data Index: 4259920 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2701. Min Range: -5.2701
Max Act: 5.0826. Min Act: -0.1700
Data Index: 5717973 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2701. Min Range: -5.2701
Max Act: 5.0513. Min Act: -0.1700
Data Index: 731891 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2701. Min Range: -5.2701
Max Act: 5.0201. Min Act: -0.1700
Data Index: 2562770 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2701. Min Range: -5.2701
Max Act: 5.0201. Min Act: -0.1700
Data Index: 4543359 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2701. Min Range: -5.2701
Max Act: 4.9576. Min Act: -0.1700
Data Index: 5001133 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2701. Min Range: -5.2701
Max Act: 4.9576. Min Act: -0.1700
Data Index: 2562762 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2701. Min Range: -5.2701
Max Act: 4.9576. Min Act: -0.1700
Data Index: 1066293 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2701. Min Range: -5.2701
Max Act: 4.9263. Min Act: -0.1700
Data Index: 731885 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2701. Min Range: -5.2701
Max Act: 4.8951. Min Act: -0.1700
Data Index: 6266882 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2701. Min Range: -5.2701
Max Act: 4.8638. Min Act: -0.1700
Data Index: 7642289 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2701. Min Range: -5.2701
Max Act: 4.8013. Min Act: -0.1700
Data Index: 2820789 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2701. Min Range: -5.2701
Max Act: 4.8013. Min Act: -0.1700
Data Index: 4302011 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2701. Min Range: -5.2701
Max Act: 4.8013. Min Act: -0.1700
Data Index: 2858914 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2701. Min Range: -5.2701
Max Act: 4.7701. Min Act: -0.1700
Data Index: 2857390 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2701. Min Range: -5.2701
Max Act: 4.7701. Min Act: -0.1700
Data Index: 411220 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2701. Min Range: -5.2701
Max Act: 4.7701. Min Act: -0.1700
Data Index: 2411033 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #19