Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5939 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8469. Min Range: -6.8469
Max Act: 6.8469. Min Act: -0.1700
Data Index: 2888591 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8469. Min Range: -6.8469
Max Act: 6.7219. Min Act: -0.1700
Data Index: 6422856 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8469. Min Range: -6.8469
Max Act: 6.6594. Min Act: -0.1700
Data Index: 6286002 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8469. Min Range: -6.8469
Max Act: 6.6282. Min Act: -0.1700
Data Index: 6856479 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8469. Min Range: -6.8469
Max Act: 6.5969. Min Act: -0.1700
Data Index: 6381668 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8469. Min Range: -6.8469
Max Act: 6.5969. Min Act: -0.1700
Data Index: 2792058 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8469. Min Range: -6.8469
Max Act: 6.5657. Min Act: -0.1700
Data Index: 3009474 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8469. Min Range: -6.8469
Max Act: 6.5344. Min Act: -0.1700
Data Index: 5079927 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8469. Min Range: -6.8469
Max Act: 6.5032. Min Act: -0.1700
Data Index: 6931880 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8469. Min Range: -6.8469
Max Act: 6.5032. Min Act: -0.1700
Data Index: 7848239 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8469. Min Range: -6.8469
Max Act: 6.4719. Min Act: -0.1700
Data Index: 558798 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8469. Min Range: -6.8469
Max Act: 6.4719. Min Act: -0.1700
Data Index: 4323832 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8469. Min Range: -6.8469
Max Act: 6.4407. Min Act: -0.1700
Data Index: 1433581 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8469. Min Range: -6.8469
Max Act: 6.4094. Min Act: -0.1700
Data Index: 1076257 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8469. Min Range: -6.8469
Max Act: 6.4094. Min Act: -0.1700
Data Index: 3950939 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8469. Min Range: -6.8469
Max Act: 6.4094. Min Act: -0.1700
Data Index: 6777033 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8469. Min Range: -6.8469
Max Act: 6.3782. Min Act: -0.1700
Data Index: 3585227 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8469. Min Range: -6.8469
Max Act: 6.3782. Min Act: -0.1700
Data Index: 6839872 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8469. Min Range: -6.8469
Max Act: 6.3782. Min Act: -0.1700
Data Index: 7692746 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8469. Min Range: -6.8469
Max Act: 6.3782. Min Act: -0.1700
Data Index: 1789554 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #19