Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2723 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.7496. Min Range: -3.7496
Max Act: 3.7496. Min Act: -0.1700
Data Index: 1936065 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7496. Min Range: -3.7496
Max Act: 3.7496. Min Act: -0.1700
Data Index: 1082972 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7496. Min Range: -3.7496
Max Act: 3.7496. Min Act: -0.1700
Data Index: 489028 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7496. Min Range: -3.7496
Max Act: 3.7184. Min Act: -0.1700
Data Index: 630506 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7496. Min Range: -3.7496
Max Act: 3.7184. Min Act: -0.1700
Data Index: 5028543 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7496. Min Range: -3.7496
Max Act: 3.7184. Min Act: -0.1700
Data Index: 7518458 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7496. Min Range: -3.7496
Max Act: 3.7184. Min Act: -0.1700
Data Index: 4469703 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7496. Min Range: -3.7496
Max Act: 3.6871. Min Act: -0.1700
Data Index: 7627449 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7496. Min Range: -3.7496
Max Act: 3.6871. Min Act: -0.1700
Data Index: 5998614 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7496. Min Range: -3.7496
Max Act: 3.6871. Min Act: -0.1700
Data Index: 1644599 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7496. Min Range: -3.7496
Max Act: 3.6871. Min Act: -0.1700
Data Index: 8434494 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7496. Min Range: -3.7496
Max Act: 3.6871. Min Act: -0.1700
Data Index: 6831100 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7496. Min Range: -3.7496
Max Act: 3.6871. Min Act: -0.1700
Data Index: 2077758 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7496. Min Range: -3.7496
Max Act: 3.6871. Min Act: -0.1700
Data Index: 4269104 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7496. Min Range: -3.7496
Max Act: 3.6871. Min Act: -0.1700
Data Index: 7013552 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7496. Min Range: -3.7496
Max Act: 3.6871. Min Act: -0.1700
Data Index: 1747781 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7496. Min Range: -3.7496
Max Act: 3.6558. Min Act: -0.1700
Data Index: 5349468 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7496. Min Range: -3.7496
Max Act: 3.6245. Min Act: -0.1700
Data Index: 5491700 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7496. Min Range: -3.7496
Max Act: 3.6558. Min Act: -0.1700
Data Index: 6042950 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7496. Min Range: -3.7496
Max Act: 3.6558. Min Act: -0.1700
Data Index: 6750843 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #19