Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4508 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5799. Min Range: -5.5799
Max Act: 5.5799. Min Act: -0.1700
Data Index: 285947 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5799. Min Range: -5.5799
Max Act: 5.4549. Min Act: -0.1700
Data Index: 5846132 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5799. Min Range: -5.5799
Max Act: 5.4549. Min Act: -0.1700
Data Index: 1496980 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5799. Min Range: -5.5799
Max Act: 5.4236. Min Act: -0.1700
Data Index: 4355822 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5799. Min Range: -5.5799
Max Act: 5.3611. Min Act: -0.1700
Data Index: 2403028 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5799. Min Range: -5.5799
Max Act: 5.3611. Min Act: -0.1700
Data Index: 8565423 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5799. Min Range: -5.5799
Max Act: 5.2986. Min Act: -0.1700
Data Index: 1310176 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5799. Min Range: -5.5799
Max Act: 5.2674. Min Act: -0.1700
Data Index: 582283 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5799. Min Range: -5.5799
Max Act: 5.2049. Min Act: -0.1700
Data Index: 2937121 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5799. Min Range: -5.5799
Max Act: 5.1736. Min Act: -0.1700
Data Index: 4353572 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5799. Min Range: -5.5799
Max Act: 5.1736. Min Act: -0.1700
Data Index: 5152620 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5799. Min Range: -5.5799
Max Act: 5.1736. Min Act: -0.1700
Data Index: 3520171 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5799. Min Range: -5.5799
Max Act: 5.1736. Min Act: -0.1700
Data Index: 6183155 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5799. Min Range: -5.5799
Max Act: 5.1736. Min Act: -0.1700
Data Index: 3611799 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5799. Min Range: -5.5799
Max Act: 5.1424. Min Act: -0.1700
Data Index: 3990124 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5799. Min Range: -5.5799
Max Act: 5.1111. Min Act: -0.1700
Data Index: 3833747 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5799. Min Range: -5.5799
Max Act: 5.1736. Min Act: -0.1700
Data Index: 5019042 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5799. Min Range: -5.5799
Max Act: 5.1424. Min Act: -0.1700
Data Index: 3578236 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5799. Min Range: -5.5799
Max Act: 5.1424. Min Act: -0.1700
Data Index: 2496893 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5799. Min Range: -5.5799
Max Act: 5.1111. Min Act: -0.1700
Data Index: 6791070 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #19