Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2885 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.6885. Min Range: -3.6885
Max Act: 3.6885. Min Act: -0.1700
Data Index: 5860769 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6885. Min Range: -3.6885
Max Act: 3.6885. Min Act: -0.1700
Data Index: 2165177 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6885. Min Range: -3.6885
Max Act: 3.6885. Min Act: -0.1700
Data Index: 3742164 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6885. Min Range: -3.6885
Max Act: 3.6572. Min Act: -0.1700
Data Index: 4606519 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6885. Min Range: -3.6885
Max Act: 3.6572. Min Act: -0.1700
Data Index: 1986206 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6885. Min Range: -3.6885
Max Act: 3.6572. Min Act: -0.1700
Data Index: 1978256 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6885. Min Range: -3.6885
Max Act: 3.6572. Min Act: -0.1700
Data Index: 6800600 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6885. Min Range: -3.6885
Max Act: 3.6259. Min Act: -0.1700
Data Index: 1376795 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6885. Min Range: -3.6885
Max Act: 3.6259. Min Act: -0.1700
Data Index: 7704912 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6885. Min Range: -3.6885
Max Act: 3.6259. Min Act: -0.1700
Data Index: 8794552 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6885. Min Range: -3.6885
Max Act: 3.6259. Min Act: -0.1700
Data Index: 6262746 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6885. Min Range: -3.6885
Max Act: 3.6259. Min Act: -0.1700
Data Index: 5892627 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6885. Min Range: -3.6885
Max Act: 3.6259. Min Act: -0.1700
Data Index: 699615 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6885. Min Range: -3.6885
Max Act: 3.6259. Min Act: -0.1700
Data Index: 251059 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6885. Min Range: -3.6885
Max Act: 3.5946. Min Act: -0.1700
Data Index: 3935751 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6885. Min Range: -3.6885
Max Act: 3.5946. Min Act: -0.1700
Data Index: 4421748 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6885. Min Range: -3.6885
Max Act: 3.5946. Min Act: -0.1700
Data Index: 4479046 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6885. Min Range: -3.6885
Max Act: 3.5946. Min Act: -0.1700
Data Index: 1114444 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6885. Min Range: -3.6885
Max Act: 3.5946. Min Act: -0.1700
Data Index: 764086 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6885. Min Range: -3.6885
Max Act: 3.5946. Min Act: -0.1700
Data Index: 4515270 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #19