Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4410 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9101. Min Range: -3.9101
Max Act: 3.9101. Min Act: -0.1700
Data Index: 6424599 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9101. Min Range: -3.9101
Max Act: 3.8788. Min Act: -0.1700
Data Index: 6034658 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9101. Min Range: -3.9101
Max Act: 3.7850. Min Act: -0.1700
Data Index: 6424591 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9101. Min Range: -3.9101
Max Act: 3.7537. Min Act: -0.1700
Data Index: 3087929 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9101. Min Range: -3.9101
Max Act: 3.7537. Min Act: -0.1700
Data Index: 3087923 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9101. Min Range: -3.9101
Max Act: 3.7224. Min Act: -0.1700
Data Index: 3087922 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9101. Min Range: -3.9101
Max Act: 3.7224. Min Act: -0.1700
Data Index: 1059067 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9101. Min Range: -3.9101
Max Act: 3.6911. Min Act: -0.1700
Data Index: 1059087 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9101. Min Range: -3.9101
Max Act: 3.6598. Min Act: -0.1700
Data Index: 3087928 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9101. Min Range: -3.9101
Max Act: 3.6911. Min Act: -0.1700
Data Index: 1250992 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9101. Min Range: -3.9101
Max Act: 3.6911. Min Act: -0.1700
Data Index: 7008798 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9101. Min Range: -3.9101
Max Act: 3.6911. Min Act: -0.1700
Data Index: 7034233 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9101. Min Range: -3.9101
Max Act: 3.6911. Min Act: -0.1700
Data Index: 3087920 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9101. Min Range: -3.9101
Max Act: 3.6598. Min Act: -0.1700
Data Index: 4419516 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9101. Min Range: -3.9101
Max Act: 3.6598. Min Act: -0.1700
Data Index: 7008822 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9101. Min Range: -3.9101
Max Act: 3.6598. Min Act: -0.1700
Data Index: 7008806 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9101. Min Range: -3.9101
Max Act: 3.6911. Min Act: -0.1700
Data Index: 1059066 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9101. Min Range: -3.9101
Max Act: 3.6598. Min Act: -0.1700
Data Index: 7008797 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9101. Min Range: -3.9101
Max Act: 3.6598. Min Act: -0.1700
Data Index: 6424600 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9101. Min Range: -3.9101
Max Act: 3.6285. Min Act: -0.1700
Data Index: 1059072 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #19