Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6321 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0644. Min Range: -4.0644
Max Act: 4.0644. Min Act: -0.1700
Data Index: 450528 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0644. Min Range: -4.0644
Max Act: 3.9707. Min Act: -0.1700
Data Index: 3090471 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0644. Min Range: -4.0644
Max Act: 3.9707. Min Act: -0.1700
Data Index: 41994 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0644. Min Range: -4.0644
Max Act: 3.9707. Min Act: -0.1700
Data Index: 6987318 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0644. Min Range: -4.0644
Max Act: 3.9394. Min Act: -0.1700
Data Index: 6102223 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0644. Min Range: -4.0644
Max Act: 3.9707. Min Act: -0.1700
Data Index: 5969930 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0644. Min Range: -4.0644
Max Act: 3.9707. Min Act: -0.1700
Data Index: 245662 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0644. Min Range: -4.0644
Max Act: 3.9707. Min Act: -0.1700
Data Index: 5262268 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0644. Min Range: -4.0644
Max Act: 3.9394. Min Act: -0.1700
Data Index: 7332798 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0644. Min Range: -4.0644
Max Act: 3.9707. Min Act: -0.1700
Data Index: 4112801 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0644. Min Range: -4.0644
Max Act: 3.9394. Min Act: -0.1700
Data Index: 4077859 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0644. Min Range: -4.0644
Max Act: 3.9707. Min Act: -0.1700
Data Index: 3251062 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0644. Min Range: -4.0644
Max Act: 3.9707. Min Act: -0.1700
Data Index: 2808014 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0644. Min Range: -4.0644
Max Act: 3.9081. Min Act: -0.1700
Data Index: 1393123 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0644. Min Range: -4.0644
Max Act: 3.9081. Min Act: -0.1700
Data Index: 4637400 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0644. Min Range: -4.0644
Max Act: 3.9081. Min Act: -0.1700
Data Index: 602197 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0644. Min Range: -4.0644
Max Act: 3.9081. Min Act: -0.1700
Data Index: 356135 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0644. Min Range: -4.0644
Max Act: 3.9081. Min Act: -0.1700
Data Index: 719494 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0644. Min Range: -4.0644
Max Act: 3.9081. Min Act: -0.1700
Data Index: 7473308 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0644. Min Range: -4.0644
Max Act: 3.9081. Min Act: -0.1700
Data Index: 6740264 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19