Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5032 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3141. Min Range: -7.3141
Max Act: 7.3141. Min Act: -0.1700
Data Index: 1216673 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3141. Min Range: -7.3141
Max Act: 7.2516. Min Act: -0.1700
Data Index: 4638620 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3141. Min Range: -7.3141
Max Act: 7.0954. Min Act: -0.1700
Data Index: 3146031 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3141. Min Range: -7.3141
Max Act: 7.0954. Min Act: -0.1700
Data Index: 6165795 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3141. Min Range: -7.3141
Max Act: 7.0641. Min Act: -0.1700
Data Index: 8449237 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3141. Min Range: -7.3141
Max Act: 7.0329. Min Act: -0.1700
Data Index: 5686607 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3141. Min Range: -7.3141
Max Act: 7.0329. Min Act: -0.1700
Data Index: 4363689 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3141. Min Range: -7.3141
Max Act: 7.0641. Min Act: -0.1700
Data Index: 5834996 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3141. Min Range: -7.3141
Max Act: 7.0329. Min Act: -0.1700
Data Index: 4276478 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3141. Min Range: -7.3141
Max Act: 7.0016. Min Act: -0.1700
Data Index: 6139550 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3141. Min Range: -7.3141
Max Act: 6.9704. Min Act: -0.1700
Data Index: 1896391 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3141. Min Range: -7.3141
Max Act: 6.9704. Min Act: -0.1700
Data Index: 7193015 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3141. Min Range: -7.3141
Max Act: 6.9391. Min Act: -0.1700
Data Index: 3651829 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3141. Min Range: -7.3141
Max Act: 6.9391. Min Act: -0.1700
Data Index: 3416395 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3141. Min Range: -7.3141
Max Act: 6.9391. Min Act: -0.1700
Data Index: 2767256 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3141. Min Range: -7.3141
Max Act: 6.9079. Min Act: -0.1700
Data Index: 6232965 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3141. Min Range: -7.3141
Max Act: 6.9079. Min Act: -0.1700
Data Index: 7252209 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3141. Min Range: -7.3141
Max Act: 6.9079. Min Act: -0.1700
Data Index: 464240 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3141. Min Range: -7.3141
Max Act: 6.8454. Min Act: -0.1700
Data Index: 5801716 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3141. Min Range: -7.3141
Max Act: 6.8454. Min Act: -0.1700
Data Index: 3219916 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #19