Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2322 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2063. Min Range: -8.2063
Max Act: 8.2063. Min Act: -0.1700
Data Index: 8062512 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2063. Min Range: -8.2063
Max Act: 7.9563. Min Act: -0.1700
Data Index: 3565718 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2063. Min Range: -8.2063
Max Act: 7.9563. Min Act: -0.1700
Data Index: 6569137 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2063. Min Range: -8.2063
Max Act: 7.9563. Min Act: -0.1700
Data Index: 7781408 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2063. Min Range: -8.2063
Max Act: 7.8938. Min Act: -0.1700
Data Index: 1681214 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2063. Min Range: -8.2063
Max Act: 7.8313. Min Act: -0.1700
Data Index: 2644156 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2063. Min Range: -8.2063
Max Act: 7.8313. Min Act: -0.1700
Data Index: 8021506 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2063. Min Range: -8.2063
Max Act: 7.8938. Min Act: -0.1700
Data Index: 6985480 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2063. Min Range: -8.2063
Max Act: 7.8313. Min Act: -0.1700
Data Index: 1004906 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2063. Min Range: -8.2063
Max Act: 7.8313. Min Act: -0.1700
Data Index: 1636368 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2063. Min Range: -8.2063
Max Act: 7.8313. Min Act: -0.1700
Data Index: 1503425 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2063. Min Range: -8.2063
Max Act: 7.8313. Min Act: -0.1700
Data Index: 5807343 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2063. Min Range: -8.2063
Max Act: 7.8313. Min Act: -0.1700
Data Index: 8014007 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2063. Min Range: -8.2063
Max Act: 7.7688. Min Act: -0.1700
Data Index: 5993739 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2063. Min Range: -8.2063
Max Act: 7.7688. Min Act: -0.1700
Data Index: 1863209 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2063. Min Range: -8.2063
Max Act: 7.7063. Min Act: -0.1700
Data Index: 1737507 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2063. Min Range: -8.2063
Max Act: 7.7688. Min Act: -0.1700
Data Index: 838206 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2063. Min Range: -8.2063
Max Act: 7.7688. Min Act: -0.1700
Data Index: 7886183 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2063. Min Range: -8.2063
Max Act: 7.7688. Min Act: -0.1700
Data Index: 5541238 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2063. Min Range: -8.2063
Max Act: 7.7688. Min Act: -0.1700
Data Index: 6210053 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #19