Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3725 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.7790. Min Range: -1.7790
Max Act: 1.7790. Min Act: -0.1700
Data Index: 5144888 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.7790. Min Range: -1.7790
Max Act: 1.6229. Min Act: -0.1700
Data Index: 8076639 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.7790. Min Range: -1.7790
Max Act: 1.5705. Min Act: -0.1700
Data Index: 7572348 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.7790. Min Range: -1.7790
Max Act: 1.5705. Min Act: -0.1700
Data Index: 8563848 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.7790. Min Range: -1.7790
Max Act: 1.5705. Min Act: -0.1700
Data Index: 447788 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.7790. Min Range: -1.7790
Max Act: 1.5705. Min Act: -0.1700
Data Index: 447824 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.7790. Min Range: -1.7790
Max Act: 1.5705. Min Act: -0.1700
Data Index: 447822 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.7790. Min Range: -1.7790
Max Act: 1.5705. Min Act: -0.1700
Data Index: 447795 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.7790. Min Range: -1.7790
Max Act: 1.5530. Min Act: -0.1700
Data Index: 447807 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.7790. Min Range: -1.7790
Max Act: 1.5705. Min Act: -0.1700
Data Index: 447817 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.7790. Min Range: -1.7790
Max Act: 1.5705. Min Act: -0.1700
Data Index: 447793 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.7790. Min Range: -1.7790
Max Act: 1.5705. Min Act: -0.1700
Data Index: 80110 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.7790. Min Range: -1.7790
Max Act: 1.5705. Min Act: -0.1700
Data Index: 447792 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.7790. Min Range: -1.7790
Max Act: 1.5705. Min Act: -0.1700
Data Index: 447804 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.7790. Min Range: -1.7790
Max Act: 1.5705. Min Act: -0.1700
Data Index: 447825 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.7790. Min Range: -1.7790
Max Act: 1.5705. Min Act: -0.1700
Data Index: 447819 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.7790. Min Range: -1.7790
Max Act: 1.5705. Min Act: -0.1700
Data Index: 447835 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.7790. Min Range: -1.7790
Max Act: 1.5705. Min Act: -0.1700
Data Index: 75908 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.7790. Min Range: -1.7790
Max Act: 1.5705. Min Act: -0.1700
Data Index: 447798 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.7790. Min Range: -1.7790
Max Act: 1.5705. Min Act: -0.1700
Data Index: 447806 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #19