Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 880 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1648. Min Range: -7.1648
Max Act: 7.1648. Min Act: -0.1700
Data Index: 2328674 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1648. Min Range: -7.1648
Max Act: 7.1648. Min Act: -0.1700
Data Index: 7155502 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1648. Min Range: -7.1648
Max Act: 7.1023. Min Act: -0.1700
Data Index: 3485734 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1648. Min Range: -7.1648
Max Act: 7.1023. Min Act: -0.1700
Data Index: 4267454 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1648. Min Range: -7.1648
Max Act: 7.1023. Min Act: -0.1700
Data Index: 1833742 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1648. Min Range: -7.1648
Max Act: 7.0398. Min Act: -0.1700
Data Index: 915470 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1648. Min Range: -7.1648
Max Act: 7.0398. Min Act: -0.1700
Data Index: 6531505 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1648. Min Range: -7.1648
Max Act: 7.0398. Min Act: -0.1700
Data Index: 3434475 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1648. Min Range: -7.1648
Max Act: 7.0398. Min Act: -0.1700
Data Index: 8554781 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1648. Min Range: -7.1648
Max Act: 7.0398. Min Act: -0.1700
Data Index: 1234133 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1648. Min Range: -7.1648
Max Act: 7.0398. Min Act: -0.1700
Data Index: 3730610 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1648. Min Range: -7.1648
Max Act: 7.0085. Min Act: -0.1700
Data Index: 7181170 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1648. Min Range: -7.1648
Max Act: 7.0085. Min Act: -0.1700
Data Index: 8781658 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1648. Min Range: -7.1648
Max Act: 7.0085. Min Act: -0.1700
Data Index: 8486222 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1648. Min Range: -7.1648
Max Act: 7.0085. Min Act: -0.1700
Data Index: 6675543 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1648. Min Range: -7.1648
Max Act: 7.0085. Min Act: -0.1700
Data Index: 4319179 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1648. Min Range: -7.1648
Max Act: 7.0085. Min Act: -0.1700
Data Index: 8169853 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1648. Min Range: -7.1648
Max Act: 7.0398. Min Act: -0.1700
Data Index: 8414031 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1648. Min Range: -7.1648
Max Act: 6.9773. Min Act: -0.1700
Data Index: 4102994 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1648. Min Range: -7.1648
Max Act: 6.9773. Min Act: -0.1700
Data Index: 7872045 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #19