Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2639 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.7914. Min Range: -5.7914
Max Act: 5.7914. Min Act: -0.1700
Data Index: 104967 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7914. Min Range: -5.7914
Max Act: 5.7914. Min Act: -0.1697
Data Index: 1260157 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7914. Min Range: -5.7914
Max Act: 5.7914. Min Act: -0.1700
Data Index: 5151741 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7914. Min Range: -5.7914
Max Act: 5.7602. Min Act: -0.1700
Data Index: 8411275 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7914. Min Range: -5.7914
Max Act: 5.7602. Min Act: -0.1700
Data Index: 3509604 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7914. Min Range: -5.7914
Max Act: 5.7602. Min Act: -0.1700
Data Index: 7123772 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7914. Min Range: -5.7914
Max Act: 5.7602. Min Act: -0.1700
Data Index: 3005304 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7914. Min Range: -5.7914
Max Act: 5.7602. Min Act: -0.1700
Data Index: 1128515 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7914. Min Range: -5.7914
Max Act: 5.7602. Min Act: -0.1700
Data Index: 6995617 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7914. Min Range: -5.7914
Max Act: 5.7602. Min Act: -0.1700
Data Index: 6950445 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7914. Min Range: -5.7914
Max Act: 5.7602. Min Act: -0.1700
Data Index: 6168025 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7914. Min Range: -5.7914
Max Act: 5.7602. Min Act: -0.1700
Data Index: 2786881 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7914. Min Range: -5.7914
Max Act: 5.7602. Min Act: -0.1700
Data Index: 6124700 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7914. Min Range: -5.7914
Max Act: 5.7602. Min Act: -0.1700
Data Index: 5705812 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7914. Min Range: -5.7914
Max Act: 5.7602. Min Act: -0.1700
Data Index: 4940142 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7914. Min Range: -5.7914
Max Act: 5.7289. Min Act: -0.1700
Data Index: 1911534 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7914. Min Range: -5.7914
Max Act: 5.7602. Min Act: -0.1700
Data Index: 4533736 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7914. Min Range: -5.7914
Max Act: 5.7602. Min Act: -0.1700
Data Index: 1889785 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7914. Min Range: -5.7914
Max Act: 5.7602. Min Act: -0.1700
Data Index: 1766069 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7914. Min Range: -5.7914
Max Act: 5.7602. Min Act: -0.1700
Data Index: 3834929 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #19