Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3571 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8452. Min Range: -7.8452
Max Act: 7.8452. Min Act: -0.1700
Data Index: 6793185 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8452. Min Range: -7.8452
Max Act: 7.6577. Min Act: -0.1700
Data Index: 6373660 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8452. Min Range: -7.8452
Max Act: 7.5952. Min Act: -0.1700
Data Index: 6830130 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8452. Min Range: -7.8452
Max Act: 7.5014. Min Act: -0.1700
Data Index: 6729239 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8452. Min Range: -7.8452
Max Act: 7.5327. Min Act: -0.1700
Data Index: 3702450 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8452. Min Range: -7.8452
Max Act: 7.5327. Min Act: -0.1700
Data Index: 434077 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8452. Min Range: -7.8452
Max Act: 7.4702. Min Act: -0.1700
Data Index: 8683583 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8452. Min Range: -7.8452
Max Act: 7.4702. Min Act: -0.1700
Data Index: 2699764 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8452. Min Range: -7.8452
Max Act: 7.4702. Min Act: -0.1700
Data Index: 2410074 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8452. Min Range: -7.8452
Max Act: 7.4702. Min Act: -0.1700
Data Index: 8358317 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8452. Min Range: -7.8452
Max Act: 7.4389. Min Act: -0.1700
Data Index: 2888463 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8452. Min Range: -7.8452
Max Act: 7.4389. Min Act: -0.1700
Data Index: 7214011 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8452. Min Range: -7.8452
Max Act: 7.4389. Min Act: -0.1700
Data Index: 3847714 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8452. Min Range: -7.8452
Max Act: 7.4077. Min Act: -0.1700
Data Index: 4481299 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8452. Min Range: -7.8452
Max Act: 7.4077. Min Act: -0.1700
Data Index: 7553705 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8452. Min Range: -7.8452
Max Act: 7.3452. Min Act: -0.1700
Data Index: 1564405 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8452. Min Range: -7.8452
Max Act: 7.3452. Min Act: -0.1700
Data Index: 4498487 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8452. Min Range: -7.8452
Max Act: 7.2827. Min Act: -0.1700
Data Index: 3406726 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8452. Min Range: -7.8452
Max Act: 7.2827. Min Act: -0.1700
Data Index: 123953 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8452. Min Range: -7.8452
Max Act: 7.2514. Min Act: -0.1700
Data Index: 7014583 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #19