Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3723 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9417. Min Range: -5.9417
Max Act: 5.9417. Min Act: -0.1700
Data Index: 4042158 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9417. Min Range: -5.9417
Max Act: 5.3480. Min Act: -0.1700
Data Index: 966537 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9417. Min Range: -5.9417
Max Act: 5.2542. Min Act: -0.1700
Data Index: 884278 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9417. Min Range: -5.9417
Max Act: 5.2230. Min Act: -0.1700
Data Index: 1886895 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9417. Min Range: -5.9417
Max Act: 5.2230. Min Act: -0.1700
Data Index: 3241318 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9417. Min Range: -5.9417
Max Act: 5.1917. Min Act: -0.1700
Data Index: 2644109 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9417. Min Range: -5.9417
Max Act: 5.1605. Min Act: -0.1700
Data Index: 2879 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9417. Min Range: -5.9417
Max Act: 5.1605. Min Act: -0.1700
Data Index: 6696048 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9417. Min Range: -5.9417
Max Act: 5.1292. Min Act: -0.1700
Data Index: 2101133 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9417. Min Range: -5.9417
Max Act: 5.1605. Min Act: -0.1700
Data Index: 346955 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9417. Min Range: -5.9417
Max Act: 5.1605. Min Act: -0.1700
Data Index: 303378 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9417. Min Range: -5.9417
Max Act: 5.1292. Min Act: -0.1700
Data Index: 3468749 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9417. Min Range: -5.9417
Max Act: 5.0980. Min Act: -0.1700
Data Index: 5547282 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9417. Min Range: -5.9417
Max Act: 5.1292. Min Act: -0.1700
Data Index: 4584902 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9417. Min Range: -5.9417
Max Act: 5.1292. Min Act: -0.1700
Data Index: 1933249 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9417. Min Range: -5.9417
Max Act: 5.1292. Min Act: -0.1700
Data Index: 7634717 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9417. Min Range: -5.9417
Max Act: 5.0980. Min Act: -0.1700
Data Index: 1044595 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9417. Min Range: -5.9417
Max Act: 5.1292. Min Act: -0.1700
Data Index: 2011012 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9417. Min Range: -5.9417
Max Act: 5.0980. Min Act: -0.1700
Data Index: 4407741 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9417. Min Range: -5.9417
Max Act: 5.0980. Min Act: -0.1700
Data Index: 6447064 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #19