Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 433 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.6992. Min Range: -1.6992
Max Act: 1.6992. Min Act: -0.1700
Data Index: 7970079 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.6992. Min Range: -1.6992
Max Act: 1.6819. Min Act: -0.1700
Data Index: 1206885 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.6992. Min Range: -1.6992
Max Act: 1.6819. Min Act: -0.1700
Data Index: 7653536 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.6992. Min Range: -1.6992
Max Act: 1.6732. Min Act: -0.1700
Data Index: 5473000 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.6992. Min Range: -1.6992
Max Act: 1.6645. Min Act: -0.1700
Data Index: 1439814 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.6992. Min Range: -1.6992
Max Act: 1.6645. Min Act: -0.1700
Data Index: 4272786 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.6992. Min Range: -1.6992
Max Act: 1.6645. Min Act: -0.1700
Data Index: 1082329 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.6992. Min Range: -1.6992
Max Act: 1.6558. Min Act: -0.1700
Data Index: 6647388 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.6992. Min Range: -1.6992
Max Act: 1.6558. Min Act: -0.1700
Data Index: 359519 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.6992. Min Range: -1.6992
Max Act: 1.6558. Min Act: -0.1700
Data Index: 2966333 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.6992. Min Range: -1.6992
Max Act: 1.6384. Min Act: -0.1700
Data Index: 5770768 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.6992. Min Range: -1.6992
Max Act: 1.6471. Min Act: -0.1700
Data Index: 8795300 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.6992. Min Range: -1.6992
Max Act: 1.6471. Min Act: -0.1700
Data Index: 5289767 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.6992. Min Range: -1.6992
Max Act: 1.6558. Min Act: -0.1700
Data Index: 1537513 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.6992. Min Range: -1.6992
Max Act: 1.6471. Min Act: -0.1700
Data Index: 7662757 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.6992. Min Range: -1.6992
Max Act: 1.6471. Min Act: -0.1700
Data Index: 4648376 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.6992. Min Range: -1.6992
Max Act: 1.6471. Min Act: -0.1700
Data Index: 4592064 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.6992. Min Range: -1.6992
Max Act: 1.6384. Min Act: -0.1700
Data Index: 3263224 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.6992. Min Range: -1.6992
Max Act: 1.6384. Min Act: -0.1700
Data Index: 5893880 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.6992. Min Range: -1.6992
Max Act: 1.6297. Min Act: -0.1700
Data Index: 4355340 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19