Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3831 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.0410. Min Range: -9.0410
Max Act: 9.0410. Min Act: -0.1700
Data Index: 1714311 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.0410. Min Range: -9.0410
Max Act: 8.4160. Min Act: -0.1700
Data Index: 7779762 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.0410. Min Range: -9.0410
Max Act: 8.2285. Min Act: -0.1700
Data Index: 6891428 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.0410. Min Range: -9.0410
Max Act: 8.1660. Min Act: -0.1700
Data Index: 7035941 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.0410. Min Range: -9.0410
Max Act: 8.1660. Min Act: -0.1700
Data Index: 960831 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.0410. Min Range: -9.0410
Max Act: 8.1035. Min Act: -0.1700
Data Index: 1064227 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.0410. Min Range: -9.0410
Max Act: 8.1035. Min Act: -0.1700
Data Index: 6492428 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.0410. Min Range: -9.0410
Max Act: 8.0410. Min Act: -0.1700
Data Index: 666302 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.0410. Min Range: -9.0410
Max Act: 8.0410. Min Act: -0.1700
Data Index: 1082379 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.0410. Min Range: -9.0410
Max Act: 8.0410. Min Act: -0.1700
Data Index: 1460832 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.0410. Min Range: -9.0410
Max Act: 8.0410. Min Act: -0.1700
Data Index: 6246398 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.0410. Min Range: -9.0410
Max Act: 8.0410. Min Act: -0.1700
Data Index: 2170970 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.0410. Min Range: -9.0410
Max Act: 7.9785. Min Act: -0.1700
Data Index: 3398014 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.0410. Min Range: -9.0410
Max Act: 8.0410. Min Act: -0.1700
Data Index: 6757776 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.0410. Min Range: -9.0410
Max Act: 7.9785. Min Act: -0.1700
Data Index: 860952 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.0410. Min Range: -9.0410
Max Act: 7.9785. Min Act: -0.1700
Data Index: 5375947 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.0410. Min Range: -9.0410
Max Act: 7.9785. Min Act: -0.1700
Data Index: 605946 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.0410. Min Range: -9.0410
Max Act: 7.9785. Min Act: -0.1700
Data Index: 2525966 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.0410. Min Range: -9.0410
Max Act: 7.9160. Min Act: -0.1700
Data Index: 1254513 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.0410. Min Range: -9.0410
Max Act: 7.9160. Min Act: -0.1700
Data Index: 36741 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #19