Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4980 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 1.8937. Min Range: -1.8937
Max Act: 1.8937. Min Act: -0.1700
Data Index: 2074799 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.8937. Min Range: -1.8937
Max Act: 1.8596. Min Act: -0.1700
Data Index: 6962229 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.8937. Min Range: -1.8937
Max Act: 1.8424. Min Act: -0.1700
Data Index: 5166470 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.8937. Min Range: -1.8937
Max Act: 1.8424. Min Act: -0.1700
Data Index: 8165027 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.8937. Min Range: -1.8937
Max Act: 1.8424. Min Act: -0.1700
Data Index: 1101053 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.8937. Min Range: -1.8937
Max Act: 1.8424. Min Act: -0.1700
Data Index: 306775 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.8937. Min Range: -1.8937
Max Act: 1.8253. Min Act: -0.1700
Data Index: 145778 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.8937. Min Range: -1.8937
Max Act: 1.8253. Min Act: -0.1700
Data Index: 2286849 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.8937. Min Range: -1.8937
Max Act: 1.8253. Min Act: -0.1700
Data Index: 3785537 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.8937. Min Range: -1.8937
Max Act: 1.8253. Min Act: -0.1700
Data Index: 5021746 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.8937. Min Range: -1.8937
Max Act: 1.8081. Min Act: -0.1700
Data Index: 4583502 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.8937. Min Range: -1.8937
Max Act: 1.8081. Min Act: -0.1700
Data Index: 5136392 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.8937. Min Range: -1.8937
Max Act: 1.8081. Min Act: -0.1700
Data Index: 824067 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.8937. Min Range: -1.8937
Max Act: 1.8081. Min Act: -0.1700
Data Index: 8112920 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.8937. Min Range: -1.8937
Max Act: 1.8081. Min Act: -0.1700
Data Index: 7219105 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.8937. Min Range: -1.8937
Max Act: 1.7909. Min Act: -0.1700
Data Index: 4747273 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.8937. Min Range: -1.8937
Max Act: 1.7909. Min Act: -0.1700
Data Index: 1877428 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.8937. Min Range: -1.8937
Max Act: 1.8081. Min Act: -0.1700
Data Index: 4273129 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.8937. Min Range: -1.8937
Max Act: 1.7909. Min Act: -0.1700
Data Index: 2067558 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.8937. Min Range: -1.8937
Max Act: 1.7909. Min Act: -0.1700
Data Index: 5408468 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19