Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1594 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.8718. Min Range: -4.8718
Max Act: 4.8718. Min Act: -0.1700
Data Index: 883881 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8718. Min Range: -4.8718
Max Act: 4.8718. Min Act: -0.1700
Data Index: 7462088 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8718. Min Range: -4.8718
Max Act: 4.8093. Min Act: -0.1700
Data Index: 7872836 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8718. Min Range: -4.8718
Max Act: 4.8093. Min Act: -0.1699
Data Index: 2345487 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8718. Min Range: -4.8718
Max Act: 4.8093. Min Act: -0.1700
Data Index: 1645443 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8718. Min Range: -4.8718
Max Act: 4.7781. Min Act: -0.1700
Data Index: 3576424 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8718. Min Range: -4.8718
Max Act: 4.7781. Min Act: -0.1700
Data Index: 1822602 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8718. Min Range: -4.8718
Max Act: 4.7468. Min Act: -0.1700
Data Index: 2447668 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8718. Min Range: -4.8718
Max Act: 4.7468. Min Act: -0.1700
Data Index: 3222301 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8718. Min Range: -4.8718
Max Act: 4.7468. Min Act: -0.1700
Data Index: 1200694 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8718. Min Range: -4.8718
Max Act: 4.7468. Min Act: -0.1700
Data Index: 7287808 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8718. Min Range: -4.8718
Max Act: 4.7156. Min Act: -0.1700
Data Index: 7091952 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8718. Min Range: -4.8718
Max Act: 4.7156. Min Act: -0.1700
Data Index: 3594715 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8718. Min Range: -4.8718
Max Act: 4.7156. Min Act: -0.1700
Data Index: 3462573 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8718. Min Range: -4.8718
Max Act: 4.7156. Min Act: -0.1700
Data Index: 7317873 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8718. Min Range: -4.8718
Max Act: 4.7156. Min Act: -0.1700
Data Index: 4155553 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8718. Min Range: -4.8718
Max Act: 4.7156. Min Act: -0.1700
Data Index: 6921561 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8718. Min Range: -4.8718
Max Act: 4.7156. Min Act: -0.1700
Data Index: 6686016 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8718. Min Range: -4.8718
Max Act: 4.6843. Min Act: -0.1700
Data Index: 6573133 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8718. Min Range: -4.8718
Max Act: 4.7156. Min Act: -0.1700
Data Index: 4970903 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19