Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2936 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8948. Min Range: -4.8948
Max Act: 4.8948. Min Act: -0.1700
Data Index: 2977932 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8948. Min Range: -4.8948
Max Act: 4.8635. Min Act: -0.1700
Data Index: 5082131 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8948. Min Range: -4.8948
Max Act: 4.8635. Min Act: -0.1700
Data Index: 1575285 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8948. Min Range: -4.8948
Max Act: 4.8635. Min Act: -0.1700
Data Index: 2610308 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8948. Min Range: -4.8948
Max Act: 4.8635. Min Act: -0.1700
Data Index: 7779469 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8948. Min Range: -4.8948
Max Act: 4.8635. Min Act: -0.1700
Data Index: 4898052 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8948. Min Range: -4.8948
Max Act: 4.8323. Min Act: -0.1700
Data Index: 3833081 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8948. Min Range: -4.8948
Max Act: 4.8323. Min Act: -0.1700
Data Index: 3847281 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8948. Min Range: -4.8948
Max Act: 4.8323. Min Act: -0.1700
Data Index: 5191265 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8948. Min Range: -4.8948
Max Act: 4.8323. Min Act: -0.1700
Data Index: 8724468 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8948. Min Range: -4.8948
Max Act: 4.8323. Min Act: -0.1700
Data Index: 716802 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8948. Min Range: -4.8948
Max Act: 4.8010. Min Act: -0.1700
Data Index: 6753442 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8948. Min Range: -4.8948
Max Act: 4.8010. Min Act: -0.1700
Data Index: 5317225 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8948. Min Range: -4.8948
Max Act: 4.8010. Min Act: -0.1700
Data Index: 7649175 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8948. Min Range: -4.8948
Max Act: 4.8010. Min Act: -0.1700
Data Index: 1857890 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8948. Min Range: -4.8948
Max Act: 4.8010. Min Act: -0.1700
Data Index: 8386295 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8948. Min Range: -4.8948
Max Act: 4.7698. Min Act: -0.1700
Data Index: 3593184 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8948. Min Range: -4.8948
Max Act: 4.7698. Min Act: -0.1700
Data Index: 497683 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8948. Min Range: -4.8948
Max Act: 4.7698. Min Act: -0.1700
Data Index: 3965481 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8948. Min Range: -4.8948
Max Act: 4.7698. Min Act: -0.1700
Data Index: 3969213 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #19