Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2593 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9996. Min Range: -6.9996
Max Act: 6.9996. Min Act: -0.1700
Data Index: 2924713 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9996. Min Range: -6.9996
Max Act: 6.9058. Min Act: -0.1700
Data Index: 7498099 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9996. Min Range: -6.9996
Max Act: 6.8746. Min Act: -0.1700
Data Index: 7979781 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9996. Min Range: -6.9996
Max Act: 6.7808. Min Act: -0.1700
Data Index: 2211022 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9996. Min Range: -6.9996
Max Act: 6.6871. Min Act: -0.1700
Data Index: 8731795 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9996. Min Range: -6.9996
Max Act: 6.7183. Min Act: -0.1700
Data Index: 7783429 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9996. Min Range: -6.9996
Max Act: 6.7183. Min Act: -0.1700
Data Index: 5797612 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9996. Min Range: -6.9996
Max Act: 6.6871. Min Act: -0.1700
Data Index: 2898236 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9996. Min Range: -6.9996
Max Act: 6.6558. Min Act: -0.1700
Data Index: 8547397 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9996. Min Range: -6.9996
Max Act: 6.6558. Min Act: -0.1700
Data Index: 3014690 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9996. Min Range: -6.9996
Max Act: 6.5933. Min Act: -0.1700
Data Index: 3412324 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9996. Min Range: -6.9996
Max Act: 6.5621. Min Act: -0.1700
Data Index: 7936414 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9996. Min Range: -6.9996
Max Act: 6.5621. Min Act: -0.1700
Data Index: 6310612 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9996. Min Range: -6.9996
Max Act: 6.5308. Min Act: -0.1700
Data Index: 8283042 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9996. Min Range: -6.9996
Max Act: 6.5308. Min Act: -0.1700
Data Index: 8794491 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9996. Min Range: -6.9996
Max Act: 6.5308. Min Act: -0.1700
Data Index: 8775967 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9996. Min Range: -6.9996
Max Act: 6.5308. Min Act: -0.1700
Data Index: 3889188 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9996. Min Range: -6.9996
Max Act: 6.4996. Min Act: -0.1700
Data Index: 7786667 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9996. Min Range: -6.9996
Max Act: 6.5308. Min Act: -0.1700
Data Index: 3336971 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9996. Min Range: -6.9996
Max Act: 6.4683. Min Act: -0.1700
Data Index: 8109387 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #19