Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1118 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.2977. Min Range: -4.2977
Max Act: 4.2977. Min Act: -0.1700
Data Index: 343681 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2977. Min Range: -4.2977
Max Act: 4.0790. Min Act: -0.1700
Data Index: 7844136 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2977. Min Range: -4.2977
Max Act: 4.0477. Min Act: -0.1700
Data Index: 8591538 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2977. Min Range: -4.2977
Max Act: 4.0477. Min Act: -0.1700
Data Index: 1033580 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2977. Min Range: -4.2977
Max Act: 3.9852. Min Act: -0.1700
Data Index: 8500804 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2977. Min Range: -4.2977
Max Act: 3.8601. Min Act: -0.1700
Data Index: 2072413 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2977. Min Range: -4.2977
Max Act: 3.8601. Min Act: -0.1700
Data Index: 5772022 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2977. Min Range: -4.2977
Max Act: 3.8914. Min Act: -0.1700
Data Index: 5567792 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2977. Min Range: -4.2977
Max Act: 3.8914. Min Act: -0.1700
Data Index: 8802319 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2977. Min Range: -4.2977
Max Act: 3.8601. Min Act: -0.1700
Data Index: 4984517 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2977. Min Range: -4.2977
Max Act: 3.8914. Min Act: -0.1700
Data Index: 3996557 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2977. Min Range: -4.2977
Max Act: 3.8289. Min Act: -0.1700
Data Index: 7444988 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2977. Min Range: -4.2977
Max Act: 3.7976. Min Act: -0.1700
Data Index: 6232715 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2977. Min Range: -4.2977
Max Act: 3.7976. Min Act: -0.1700
Data Index: 6005983 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2977. Min Range: -4.2977
Max Act: 3.7976. Min Act: -0.1700
Data Index: 293839 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2977. Min Range: -4.2977
Max Act: 3.7663. Min Act: -0.1700
Data Index: 7560981 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2977. Min Range: -4.2977
Max Act: 3.7663. Min Act: -0.1700
Data Index: 3039760 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2977. Min Range: -4.2977
Max Act: 3.7350. Min Act: -0.1700
Data Index: 948631 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2977. Min Range: -4.2977
Max Act: 3.7350. Min Act: -0.1700
Data Index: 8101771 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2977. Min Range: -4.2977
Max Act: 3.7037. Min Act: -0.1700
Data Index: 3658748 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #19