Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5947 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9379. Min Range: -5.9379
Max Act: 5.9379. Min Act: -0.1700
Data Index: 5829226 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9379. Min Range: -5.9379
Max Act: 5.5317. Min Act: -0.1700
Data Index: 5803357 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9379. Min Range: -5.9379
Max Act: 5.5004. Min Act: -0.1700
Data Index: 3988039 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9379. Min Range: -5.9379
Max Act: 5.4379. Min Act: -0.1700
Data Index: 2837281 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9379. Min Range: -5.9379
Max Act: 5.4379. Min Act: -0.1700
Data Index: 4413605 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9379. Min Range: -5.9379
Max Act: 5.4379. Min Act: -0.1700
Data Index: 3462897 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9379. Min Range: -5.9379
Max Act: 5.4379. Min Act: -0.1700
Data Index: 6078905 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9379. Min Range: -5.9379
Max Act: 5.4067. Min Act: -0.1700
Data Index: 8629528 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9379. Min Range: -5.9379
Max Act: 5.4067. Min Act: -0.1700
Data Index: 5736847 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9379. Min Range: -5.9379
Max Act: 5.3754. Min Act: -0.1700
Data Index: 2582816 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9379. Min Range: -5.9379
Max Act: 5.3442. Min Act: -0.1700
Data Index: 1423029 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9379. Min Range: -5.9379
Max Act: 5.2817. Min Act: -0.1700
Data Index: 158206 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9379. Min Range: -5.9379
Max Act: 5.3129. Min Act: -0.1700
Data Index: 5330605 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9379. Min Range: -5.9379
Max Act: 5.3442. Min Act: -0.1700
Data Index: 8410821 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9379. Min Range: -5.9379
Max Act: 5.2817. Min Act: -0.1700
Data Index: 3918031 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9379. Min Range: -5.9379
Max Act: 5.2817. Min Act: -0.1700
Data Index: 7568475 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9379. Min Range: -5.9379
Max Act: 5.2504. Min Act: -0.1700
Data Index: 4686711 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9379. Min Range: -5.9379
Max Act: 5.2504. Min Act: -0.1700
Data Index: 7370738 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9379. Min Range: -5.9379
Max Act: 5.2504. Min Act: -0.1700
Data Index: 471954 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9379. Min Range: -5.9379
Max Act: 5.2504. Min Act: -0.1700
Data Index: 4743055 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #19