Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4316 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4891. Min Range: -6.4891
Max Act: 6.4891. Min Act: -0.1700
Data Index: 4960966 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4891. Min Range: -6.4891
Max Act: 6.0828. Min Act: -0.1700
Data Index: 7286006 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4891. Min Range: -6.4891
Max Act: 6.0516. Min Act: -0.1700
Data Index: 6536108 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4891. Min Range: -6.4891
Max Act: 5.9891. Min Act: -0.1700
Data Index: 6154876 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4891. Min Range: -6.4891
Max Act: 5.8953. Min Act: -0.1700
Data Index: 3396431 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4891. Min Range: -6.4891
Max Act: 5.8953. Min Act: -0.1700
Data Index: 4585691 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4891. Min Range: -6.4891
Max Act: 5.8953. Min Act: -0.1700
Data Index: 7485291 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4891. Min Range: -6.4891
Max Act: 5.8641. Min Act: -0.1700
Data Index: 5702613 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4891. Min Range: -6.4891
Max Act: 5.8641. Min Act: -0.1700
Data Index: 8501698 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4891. Min Range: -6.4891
Max Act: 5.8328. Min Act: -0.1700
Data Index: 1033678 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4891. Min Range: -6.4891
Max Act: 5.8953. Min Act: -0.1700
Data Index: 8149164 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4891. Min Range: -6.4891
Max Act: 5.8328. Min Act: -0.1700
Data Index: 5532693 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4891. Min Range: -6.4891
Max Act: 5.8016. Min Act: -0.1700
Data Index: 6104275 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4891. Min Range: -6.4891
Max Act: 5.8328. Min Act: -0.1700
Data Index: 5582046 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4891. Min Range: -6.4891
Max Act: 5.8328. Min Act: -0.1700
Data Index: 7921181 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4891. Min Range: -6.4891
Max Act: 5.7703. Min Act: -0.1700
Data Index: 6998655 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4891. Min Range: -6.4891
Max Act: 5.7703. Min Act: -0.1700
Data Index: 4694678 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4891. Min Range: -6.4891
Max Act: 5.7391. Min Act: -0.1700
Data Index: 8037267 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4891. Min Range: -6.4891
Max Act: 5.7391. Min Act: -0.1700
Data Index: 890188 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4891. Min Range: -6.4891
Max Act: 5.7391. Min Act: -0.1700
Data Index: 350294 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #19