Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4036 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0265. Min Range: -8.0265
Max Act: 8.0265. Min Act: -0.1700
Data Index: 3343784 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0265. Min Range: -8.0265
Max Act: 7.4015. Min Act: -0.1700
Data Index: 1622114 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0265. Min Range: -8.0265
Max Act: 7.3078. Min Act: -0.1700
Data Index: 830235 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0265. Min Range: -8.0265
Max Act: 7.1828. Min Act: -0.1700
Data Index: 1143327 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0265. Min Range: -8.0265
Max Act: 7.1515. Min Act: -0.1700
Data Index: 7866520 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0265. Min Range: -8.0265
Max Act: 7.0890. Min Act: -0.1700
Data Index: 8741949 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0265. Min Range: -8.0265
Max Act: 7.0578. Min Act: -0.1700
Data Index: 6985894 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0265. Min Range: -8.0265
Max Act: 6.9953. Min Act: -0.1700
Data Index: 4307352 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0265. Min Range: -8.0265
Max Act: 6.9640. Min Act: -0.1700
Data Index: 8789218 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0265. Min Range: -8.0265
Max Act: 6.8703. Min Act: -0.1700
Data Index: 6145448 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0265. Min Range: -8.0265
Max Act: 6.8078. Min Act: -0.1700
Data Index: 5829029 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0265. Min Range: -8.0265
Max Act: 6.7765. Min Act: -0.1700
Data Index: 4096691 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0265. Min Range: -8.0265
Max Act: 6.7765. Min Act: -0.1700
Data Index: 8570101 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0265. Min Range: -8.0265
Max Act: 6.7140. Min Act: -0.1700
Data Index: 7451870 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0265. Min Range: -8.0265
Max Act: 6.6828. Min Act: -0.1700
Data Index: 7050424 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0265. Min Range: -8.0265
Max Act: 6.6203. Min Act: -0.1700
Data Index: 1633986 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0265. Min Range: -8.0265
Max Act: 6.6203. Min Act: -0.1700
Data Index: 5334099 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0265. Min Range: -8.0265
Max Act: 6.5890. Min Act: -0.1700
Data Index: 8817406 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0265. Min Range: -8.0265
Max Act: 6.6203. Min Act: -0.1700
Data Index: 5450123 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0265. Min Range: -8.0265
Max Act: 6.5890. Min Act: -0.1700
Data Index: 8617566 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #19