Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3716 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9620. Min Range: -5.9620
Max Act: 5.9620. Min Act: -0.1700
Data Index: 7367435 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9620. Min Range: -5.9620
Max Act: 5.8995. Min Act: -0.1700
Data Index: 5225267 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9620. Min Range: -5.9620
Max Act: 5.8057. Min Act: -0.1700
Data Index: 2638202 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9620. Min Range: -5.9620
Max Act: 5.8057. Min Act: -0.1700
Data Index: 2722417 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9620. Min Range: -5.9620
Max Act: 5.8057. Min Act: -0.1700
Data Index: 2502940 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9620. Min Range: -5.9620
Max Act: 5.8057. Min Act: -0.1700
Data Index: 2952331 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9620. Min Range: -5.9620
Max Act: 5.8057. Min Act: -0.1700
Data Index: 3449193 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9620. Min Range: -5.9620
Max Act: 5.8057. Min Act: -0.1700
Data Index: 1979152 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9620. Min Range: -5.9620
Max Act: 5.8057. Min Act: -0.1700
Data Index: 3058696 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9620. Min Range: -5.9620
Max Act: 5.8057. Min Act: -0.1700
Data Index: 237041 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9620. Min Range: -5.9620
Max Act: 5.8057. Min Act: -0.1700
Data Index: 3042159 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9620. Min Range: -5.9620
Max Act: 5.8057. Min Act: -0.1700
Data Index: 1417984 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9620. Min Range: -5.9620
Max Act: 5.8057. Min Act: -0.1700
Data Index: 709293 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9620. Min Range: -5.9620
Max Act: 5.8057. Min Act: -0.1700
Data Index: 2877457 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9620. Min Range: -5.9620
Max Act: 5.8057. Min Act: -0.1700
Data Index: 148403 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9620. Min Range: -5.9620
Max Act: 5.8057. Min Act: -0.1700
Data Index: 2815016 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9620. Min Range: -5.9620
Max Act: 5.8057. Min Act: -0.1700
Data Index: 862186 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9620. Min Range: -5.9620
Max Act: 5.8057. Min Act: -0.1700
Data Index: 515924 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9620. Min Range: -5.9620
Max Act: 5.8057. Min Act: -0.1700
Data Index: 154363 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9620. Min Range: -5.9620
Max Act: 5.8057. Min Act: -0.1700
Data Index: 3051088 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19