Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5475 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2080. Min Range: -6.2080
Max Act: 6.2080. Min Act: -0.1700
Data Index: 2469662 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2080. Min Range: -6.2080
Max Act: 6.0830. Min Act: -0.1700
Data Index: 2649448 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2080. Min Range: -6.2080
Max Act: 5.9892. Min Act: -0.1700
Data Index: 1720120 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2080. Min Range: -6.2080
Max Act: 5.9267. Min Act: -0.1700
Data Index: 2672133 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2080. Min Range: -6.2080
Max Act: 5.9267. Min Act: -0.1700
Data Index: 2428212 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2080. Min Range: -6.2080
Max Act: 5.8642. Min Act: -0.1700
Data Index: 90550 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2080. Min Range: -6.2080
Max Act: 5.8955. Min Act: -0.1700
Data Index: 7382107 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2080. Min Range: -6.2080
Max Act: 5.8642. Min Act: -0.1700
Data Index: 7506689 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2080. Min Range: -6.2080
Max Act: 5.8642. Min Act: -0.1700
Data Index: 4190076 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2080. Min Range: -6.2080
Max Act: 5.8955. Min Act: -0.1700
Data Index: 7568134 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2080. Min Range: -6.2080
Max Act: 5.8642. Min Act: -0.1700
Data Index: 3580071 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2080. Min Range: -6.2080
Max Act: 5.8955. Min Act: -0.1700
Data Index: 4190077 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2080. Min Range: -6.2080
Max Act: 5.8642. Min Act: -0.1700
Data Index: 8207256 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2080. Min Range: -6.2080
Max Act: 5.8642. Min Act: -0.1700
Data Index: 1895416 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2080. Min Range: -6.2080
Max Act: 5.8330. Min Act: -0.1700
Data Index: 1822165 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2080. Min Range: -6.2080
Max Act: 5.8642. Min Act: -0.1700
Data Index: 2746814 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2080. Min Range: -6.2080
Max Act: 5.8642. Min Act: -0.1700
Data Index: 7307128 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2080. Min Range: -6.2080
Max Act: 5.8642. Min Act: -0.1700
Data Index: 4190075 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2080. Min Range: -6.2080
Max Act: 5.8330. Min Act: -0.1700
Data Index: 1532477 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2080. Min Range: -6.2080
Max Act: 5.8330. Min Act: -0.1700
Data Index: 2290848 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #19