Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2353 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8558. Min Range: -5.8558
Max Act: 5.8558. Min Act: -0.1700
Data Index: 5639064 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8558. Min Range: -5.8558
Max Act: 5.8558. Min Act: -0.1700
Data Index: 5313299 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8558. Min Range: -5.8558
Max Act: 5.7308. Min Act: -0.1700
Data Index: 2167446 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8558. Min Range: -5.8558
Max Act: 5.7308. Min Act: -0.1700
Data Index: 1436269 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8558. Min Range: -5.8558
Max Act: 5.6995. Min Act: -0.1700
Data Index: 7061931 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8558. Min Range: -5.8558
Max Act: 5.6683. Min Act: -0.1700
Data Index: 7740093 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8558. Min Range: -5.8558
Max Act: 5.6370. Min Act: -0.1700
Data Index: 1297094 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8558. Min Range: -5.8558
Max Act: 5.6370. Min Act: -0.1700
Data Index: 7740099 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8558. Min Range: -5.8558
Max Act: 5.6370. Min Act: -0.1700
Data Index: 3935776 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8558. Min Range: -5.8558
Max Act: 5.6058. Min Act: -0.1700
Data Index: 586723 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8558. Min Range: -5.8558
Max Act: 5.6058. Min Act: -0.1700
Data Index: 2743881 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8558. Min Range: -5.8558
Max Act: 5.5120. Min Act: -0.1700
Data Index: 3724380 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8558. Min Range: -5.8558
Max Act: 5.5745. Min Act: -0.1700
Data Index: 6366649 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8558. Min Range: -5.8558
Max Act: 5.5433. Min Act: -0.1700
Data Index: 2670132 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8558. Min Range: -5.8558
Max Act: 5.5120. Min Act: -0.1700
Data Index: 2557533 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8558. Min Range: -5.8558
Max Act: 5.5120. Min Act: -0.1700
Data Index: 7141314 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8558. Min Range: -5.8558
Max Act: 5.4808. Min Act: -0.1700
Data Index: 3712616 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8558. Min Range: -5.8558
Max Act: 5.5120. Min Act: -0.1700
Data Index: 7740094 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8558. Min Range: -5.8558
Max Act: 5.4808. Min Act: -0.1700
Data Index: 3468335 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8558. Min Range: -5.8558
Max Act: 5.4495. Min Act: -0.1700
Data Index: 1100647 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #19