Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 391 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.7835. Min Range: -2.7835
Max Act: 2.7835. Min Act: -0.1700
Data Index: 790146 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7835. Min Range: -2.7835
Max Act: 2.7835. Min Act: -0.1700
Data Index: 8164596 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7835. Min Range: -2.7835
Max Act: 2.7835. Min Act: -0.1700
Data Index: 3274509 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7835. Min Range: -2.7835
Max Act: 2.7676. Min Act: -0.1700
Data Index: 7741992 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7835. Min Range: -2.7835
Max Act: 2.7676. Min Act: -0.1700
Data Index: 7680868 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7835. Min Range: -2.7835
Max Act: 2.7516. Min Act: -0.1700
Data Index: 2759737 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7835. Min Range: -2.7835
Max Act: 2.7676. Min Act: -0.1700
Data Index: 5715269 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7835. Min Range: -2.7835
Max Act: 2.7676. Min Act: -0.1700
Data Index: 1489339 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7835. Min Range: -2.7835
Max Act: 2.7676. Min Act: -0.1700
Data Index: 6876648 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7835. Min Range: -2.7835
Max Act: 2.7676. Min Act: -0.1700
Data Index: 8561486 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7835. Min Range: -2.7835
Max Act: 2.7676. Min Act: -0.1700
Data Index: 7941780 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7835. Min Range: -2.7835
Max Act: 2.7357. Min Act: -0.1700
Data Index: 7478055 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7835. Min Range: -2.7835
Max Act: 2.7197. Min Act: -0.1700
Data Index: 3871390 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7835. Min Range: -2.7835
Max Act: 2.7357. Min Act: -0.1700
Data Index: 4084936 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7835. Min Range: -2.7835
Max Act: 2.6877. Min Act: -0.1700
Data Index: 8109564 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7835. Min Range: -2.7835
Max Act: 2.6717. Min Act: -0.1700
Data Index: 3536471 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7835. Min Range: -2.7835
Max Act: 2.6717. Min Act: -0.1700
Data Index: 3954330 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7835. Min Range: -2.7835
Max Act: 2.6717. Min Act: -0.1700
Data Index: 5488991 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7835. Min Range: -2.7835
Max Act: 2.6877. Min Act: -0.1700
Data Index: 2882863 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7835. Min Range: -2.7835
Max Act: 2.6556. Min Act: -0.1700
Data Index: 6632929 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #19