Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2505 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.1328. Min Range: -3.1328
Max Act: 3.1013. Min Act: -0.1700
Data Index: 6325149 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1328. Min Range: -3.1328
Max Act: 3.1328. Min Act: -0.1700
Data Index: 3276898 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1328. Min Range: -3.1328
Max Act: 3.1013. Min Act: -0.1700
Data Index: 6397994 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1328. Min Range: -3.1328
Max Act: 3.1013. Min Act: -0.1700
Data Index: 4494091 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1328. Min Range: -3.1328
Max Act: 3.1013. Min Act: -0.1700
Data Index: 7651922 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1328. Min Range: -3.1328
Max Act: 3.1013. Min Act: -0.1700
Data Index: 4332554 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1328. Min Range: -3.1328
Max Act: 3.1013. Min Act: -0.1700
Data Index: 4149533 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1328. Min Range: -3.1328
Max Act: 3.1013. Min Act: -0.1700
Data Index: 7169018 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1328. Min Range: -3.1328
Max Act: 3.1013. Min Act: -0.1700
Data Index: 7015694 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1328. Min Range: -3.1328
Max Act: 3.1013. Min Act: -0.1700
Data Index: 2722051 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1328. Min Range: -3.1328
Max Act: 3.0698. Min Act: -0.1700
Data Index: 7151687 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1328. Min Range: -3.1328
Max Act: 3.0698. Min Act: -0.1700
Data Index: 1224542 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1328. Min Range: -3.1328
Max Act: 3.0698. Min Act: -0.1700
Data Index: 7441018 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1328. Min Range: -3.1328
Max Act: 3.0698. Min Act: -0.1700
Data Index: 5731011 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1328. Min Range: -3.1328
Max Act: 3.0698. Min Act: -0.1700
Data Index: 4226339 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1328. Min Range: -3.1328
Max Act: 3.0698. Min Act: -0.1700
Data Index: 2529128 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1328. Min Range: -3.1328
Max Act: 3.0698. Min Act: -0.1700
Data Index: 304098 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1328. Min Range: -3.1328
Max Act: 3.0540. Min Act: -0.1700
Data Index: 4135550 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1328. Min Range: -3.1328
Max Act: 3.0540. Min Act: -0.1700
Data Index: 5826314 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1328. Min Range: -3.1328
Max Act: 3.0540. Min Act: -0.1700
Data Index: 5928860 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19