Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3497 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9509. Min Range: -6.9509
Max Act: 6.9509. Min Act: -0.1700
Data Index: 2210937 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9509. Min Range: -6.9509
Max Act: 6.9509. Min Act: -0.1700
Data Index: 5018988 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9509. Min Range: -6.9509
Max Act: 6.9197. Min Act: -0.1700
Data Index: 2210938 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9509. Min Range: -6.9509
Max Act: 6.8884. Min Act: -0.1700
Data Index: 2210934 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9509. Min Range: -6.9509
Max Act: 6.8884. Min Act: -0.1700
Data Index: 5018983 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9509. Min Range: -6.9509
Max Act: 6.9197. Min Act: -0.1700
Data Index: 7301932 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9509. Min Range: -6.9509
Max Act: 6.8572. Min Act: -0.1700
Data Index: 7567392 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9509. Min Range: -6.9509
Max Act: 6.8259. Min Act: -0.1700
Data Index: 5631542 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9509. Min Range: -6.9509
Max Act: 6.8259. Min Act: -0.1700
Data Index: 3956253 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9509. Min Range: -6.9509
Max Act: 6.7947. Min Act: -0.1700
Data Index: 2210935 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9509. Min Range: -6.9509
Max Act: 6.7634. Min Act: -0.1700
Data Index: 6025554 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9509. Min Range: -6.9509
Max Act: 6.7634. Min Act: -0.1700
Data Index: 5386479 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9509. Min Range: -6.9509
Max Act: 6.7634. Min Act: -0.1700
Data Index: 7731922 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9509. Min Range: -6.9509
Max Act: 6.7322. Min Act: -0.1700
Data Index: 4713268 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9509. Min Range: -6.9509
Max Act: 6.7634. Min Act: -0.1700
Data Index: 263411 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9509. Min Range: -6.9509
Max Act: 6.7009. Min Act: -0.1700
Data Index: 85294 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9509. Min Range: -6.9509
Max Act: 6.7009. Min Act: -0.1700
Data Index: 6593550 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9509. Min Range: -6.9509
Max Act: 6.6697. Min Act: -0.1700
Data Index: 8538601 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9509. Min Range: -6.9509
Max Act: 6.7009. Min Act: -0.1700
Data Index: 5412306 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9509. Min Range: -6.9509
Max Act: 6.7009. Min Act: -0.1700
Data Index: 7317589 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #19