Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1814 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.8813. Min Range: -5.8813
Max Act: 5.8813. Min Act: -0.1700
Data Index: 8517916 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8813. Min Range: -5.8813
Max Act: 5.7875. Min Act: -0.1700
Data Index: 4438729 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8813. Min Range: -5.8813
Max Act: 5.8188. Min Act: -0.1700
Data Index: 4712256 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8813. Min Range: -5.8813
Max Act: 5.7875. Min Act: -0.1700
Data Index: 3274868 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8813. Min Range: -5.8813
Max Act: 5.7875. Min Act: -0.1700
Data Index: 1210810 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8813. Min Range: -5.8813
Max Act: 5.7250. Min Act: -0.1700
Data Index: 7342525 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8813. Min Range: -5.8813
Max Act: 5.6938. Min Act: -0.1700
Data Index: 4316317 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8813. Min Range: -5.8813
Max Act: 5.6625. Min Act: -0.1700
Data Index: 6123705 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8813. Min Range: -5.8813
Max Act: 5.6313. Min Act: -0.1700
Data Index: 8462058 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8813. Min Range: -5.8813
Max Act: 5.6000. Min Act: -0.1700
Data Index: 8225709 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8813. Min Range: -5.8813
Max Act: 5.5688. Min Act: -0.1700
Data Index: 5278969 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8813. Min Range: -5.8813
Max Act: 5.5688. Min Act: -0.1700
Data Index: 3255577 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8813. Min Range: -5.8813
Max Act: 5.5688. Min Act: -0.1700
Data Index: 8611095 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8813. Min Range: -5.8813
Max Act: 5.6000. Min Act: -0.1700
Data Index: 6031377 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8813. Min Range: -5.8813
Max Act: 5.5688. Min Act: -0.1700
Data Index: 2399785 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8813. Min Range: -5.8813
Max Act: 5.5688. Min Act: -0.1700
Data Index: 6399606 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8813. Min Range: -5.8813
Max Act: 5.5375. Min Act: -0.1700
Data Index: 2415375 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8813. Min Range: -5.8813
Max Act: 5.5688. Min Act: -0.1700
Data Index: 261054 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8813. Min Range: -5.8813
Max Act: 5.5375. Min Act: -0.1700
Data Index: 4342458 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8813. Min Range: -5.8813
Max Act: 5.5063. Min Act: -0.1700
Data Index: 4118282 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #19