Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3008 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8071. Min Range: -6.8071
Max Act: 6.8071. Min Act: -0.1700
Data Index: 3779137 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8071. Min Range: -6.8071
Max Act: 6.8071. Min Act: -0.1700
Data Index: 5178467 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8071. Min Range: -6.8071
Max Act: 6.8071. Min Act: -0.1700
Data Index: 5996328 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8071. Min Range: -6.8071
Max Act: 6.8071. Min Act: -0.1700
Data Index: 7831801 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8071. Min Range: -6.8071
Max Act: 6.8071. Min Act: -0.1700
Data Index: 7907806 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8071. Min Range: -6.8071
Max Act: 6.8071. Min Act: -0.1700
Data Index: 3046474 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8071. Min Range: -6.8071
Max Act: 6.7758. Min Act: -0.1700
Data Index: 2190988 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8071. Min Range: -6.8071
Max Act: 6.7758. Min Act: -0.1700
Data Index: 166837 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8071. Min Range: -6.8071
Max Act: 6.7758. Min Act: -0.1700
Data Index: 2187762 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8071. Min Range: -6.8071
Max Act: 6.7758. Min Act: -0.1700
Data Index: 2092214 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8071. Min Range: -6.8071
Max Act: 6.7758. Min Act: -0.1700
Data Index: 2071043 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8071. Min Range: -6.8071
Max Act: 6.7758. Min Act: -0.1700
Data Index: 1909893 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8071. Min Range: -6.8071
Max Act: 6.7758. Min Act: -0.1700
Data Index: 1901993 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8071. Min Range: -6.8071
Max Act: 6.7758. Min Act: -0.1700
Data Index: 1695942 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8071. Min Range: -6.8071
Max Act: 6.7758. Min Act: -0.1700
Data Index: 480865 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8071. Min Range: -6.8071
Max Act: 6.7758. Min Act: -0.1700
Data Index: 1686109 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8071. Min Range: -6.8071
Max Act: 6.7758. Min Act: -0.1700
Data Index: 1655014 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8071. Min Range: -6.8071
Max Act: 6.7758. Min Act: -0.1700
Data Index: 319869 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8071. Min Range: -6.8071
Max Act: 6.7758. Min Act: -0.1700
Data Index: 272838 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8071. Min Range: -6.8071
Max Act: 6.7758. Min Act: -0.1700
Data Index: 1605723 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #19