Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4309 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.5830. Min Range: -8.5830
Max Act: 8.5830. Min Act: -0.1700
Data Index: 4635014 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5830. Min Range: -8.5830
Max Act: 8.5205. Min Act: -0.1700
Data Index: 771405 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5830. Min Range: -8.5830
Max Act: 8.5205. Min Act: -0.1700
Data Index: 7852115 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5830. Min Range: -8.5830
Max Act: 8.5205. Min Act: -0.1700
Data Index: 2738165 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5830. Min Range: -8.5830
Max Act: 8.2705. Min Act: -0.1700
Data Index: 8248852 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5830. Min Range: -8.5830
Max Act: 8.2080. Min Act: -0.1700
Data Index: 6671454 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5830. Min Range: -8.5830
Max Act: 8.0830. Min Act: -0.1700
Data Index: 6347112 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5830. Min Range: -8.5830
Max Act: 8.0830. Min Act: -0.1700
Data Index: 1659957 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5830. Min Range: -8.5830
Max Act: 8.0830. Min Act: -0.1700
Data Index: 2515469 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5830. Min Range: -8.5830
Max Act: 8.0830. Min Act: -0.1700
Data Index: 7207128 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5830. Min Range: -8.5830
Max Act: 8.0205. Min Act: -0.1700
Data Index: 6339158 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5830. Min Range: -8.5830
Max Act: 8.0205. Min Act: -0.1700
Data Index: 1469772 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5830. Min Range: -8.5830
Max Act: 7.9580. Min Act: -0.1700
Data Index: 2515456 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5830. Min Range: -8.5830
Max Act: 7.8955. Min Act: -0.1700
Data Index: 2018416 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5830. Min Range: -8.5830
Max Act: 7.8955. Min Act: -0.1700
Data Index: 2419886 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5830. Min Range: -8.5830
Max Act: 7.8955. Min Act: -0.1700
Data Index: 2122060 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5830. Min Range: -8.5830
Max Act: 7.8955. Min Act: -0.1700
Data Index: 3280055 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5830. Min Range: -8.5830
Max Act: 7.8955. Min Act: -0.1700
Data Index: 4035680 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5830. Min Range: -8.5830
Max Act: 7.8955. Min Act: -0.1700
Data Index: 7997863 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5830. Min Range: -8.5830
Max Act: 7.8955. Min Act: -0.1700
Data Index: 3327390 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #19