Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1234 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.1751. Min Range: -6.1751
Max Act: 6.1751. Min Act: -0.1700
Data Index: 2956336 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1751. Min Range: -6.1751
Max Act: 5.9876. Min Act: -0.1700
Data Index: 7229933 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1751. Min Range: -6.1751
Max Act: 5.8626. Min Act: -0.1700
Data Index: 792480 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1751. Min Range: -6.1751
Max Act: 5.8314. Min Act: -0.1700
Data Index: 4289987 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1751. Min Range: -6.1751
Max Act: 5.8001. Min Act: -0.1700
Data Index: 2030053 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1751. Min Range: -6.1751
Max Act: 5.8001. Min Act: -0.1700
Data Index: 8069835 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1751. Min Range: -6.1751
Max Act: 5.7376. Min Act: -0.1700
Data Index: 2233704 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1751. Min Range: -6.1751
Max Act: 5.7376. Min Act: -0.1700
Data Index: 7084305 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1751. Min Range: -6.1751
Max Act: 5.7376. Min Act: -0.1700
Data Index: 6764664 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1751. Min Range: -6.1751
Max Act: 5.7064. Min Act: -0.1700
Data Index: 8125937 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1751. Min Range: -6.1751
Max Act: 5.6751. Min Act: -0.1700
Data Index: 7513107 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1751. Min Range: -6.1751
Max Act: 5.6126. Min Act: -0.1700
Data Index: 8711165 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1751. Min Range: -6.1751
Max Act: 5.5814. Min Act: -0.1700
Data Index: 986289 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1751. Min Range: -6.1751
Max Act: 5.5814. Min Act: -0.1700
Data Index: 8646054 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1751. Min Range: -6.1751
Max Act: 5.5814. Min Act: -0.1700
Data Index: 7408122 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1751. Min Range: -6.1751
Max Act: 5.5501. Min Act: -0.1700
Data Index: 6644354 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1751. Min Range: -6.1751
Max Act: 5.5814. Min Act: -0.1700
Data Index: 1472094 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1751. Min Range: -6.1751
Max Act: 5.5501. Min Act: -0.1700
Data Index: 6265009 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1751. Min Range: -6.1751
Max Act: 5.5189. Min Act: -0.1700
Data Index: 894809 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1751. Min Range: -6.1751
Max Act: 5.5189. Min Act: -0.1700
Data Index: 4577766 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #19