Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4076 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9767. Min Range: -5.9767
Max Act: 5.9767. Min Act: -0.1700
Data Index: 8396714 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9767. Min Range: -5.9767
Max Act: 5.9454. Min Act: -0.1700
Data Index: 5224195 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9767. Min Range: -5.9767
Max Act: 5.9454. Min Act: -0.1700
Data Index: 6811598 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9767. Min Range: -5.9767
Max Act: 5.9767. Min Act: -0.1700
Data Index: 8237804 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9767. Min Range: -5.9767
Max Act: 5.8829. Min Act: -0.1700
Data Index: 5430275 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9767. Min Range: -5.9767
Max Act: 5.8829. Min Act: -0.1700
Data Index: 334733 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9767. Min Range: -5.9767
Max Act: 5.8517. Min Act: -0.1700
Data Index: 358789 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9767. Min Range: -5.9767
Max Act: 5.8204. Min Act: -0.1700
Data Index: 2739010 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9767. Min Range: -5.9767
Max Act: 5.8204. Min Act: -0.1700
Data Index: 1653094 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9767. Min Range: -5.9767
Max Act: 5.8204. Min Act: -0.1700
Data Index: 4800563 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9767. Min Range: -5.9767
Max Act: 5.7892. Min Act: -0.1700
Data Index: 5030698 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9767. Min Range: -5.9767
Max Act: 5.7267. Min Act: -0.1700
Data Index: 7086560 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9767. Min Range: -5.9767
Max Act: 5.7267. Min Act: -0.1700
Data Index: 7021632 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9767. Min Range: -5.9767
Max Act: 5.7267. Min Act: -0.1700
Data Index: 609488 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9767. Min Range: -5.9767
Max Act: 5.6954. Min Act: -0.1700
Data Index: 3040323 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9767. Min Range: -5.9767
Max Act: 5.6329. Min Act: -0.1700
Data Index: 2586033 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9767. Min Range: -5.9767
Max Act: 5.6329. Min Act: -0.1700
Data Index: 4332643 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9767. Min Range: -5.9767
Max Act: 5.6329. Min Act: -0.1700
Data Index: 6274623 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9767. Min Range: -5.9767
Max Act: 5.6329. Min Act: -0.1700
Data Index: 1808556 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9767. Min Range: -5.9767
Max Act: 5.6017. Min Act: -0.1700
Data Index: 7952065 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #19