Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3204 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.8410. Min Range: -8.8410
Max Act: 8.8410. Min Act: -0.1700
Data Index: 5361663 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.8410. Min Range: -8.8410
Max Act: 8.8410. Min Act: -0.1700
Data Index: 7401028 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.8410. Min Range: -8.8410
Max Act: 8.7160. Min Act: -0.1700
Data Index: 2080412 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.8410. Min Range: -8.8410
Max Act: 8.7160. Min Act: -0.1700
Data Index: 5658775 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.8410. Min Range: -8.8410
Max Act: 8.6535. Min Act: -0.1700
Data Index: 4966185 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.8410. Min Range: -8.8410
Max Act: 8.6535. Min Act: -0.1700
Data Index: 2144206 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.8410. Min Range: -8.8410
Max Act: 8.5910. Min Act: -0.1700
Data Index: 11322 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.8410. Min Range: -8.8410
Max Act: 8.5285. Min Act: -0.1700
Data Index: 2082005 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.8410. Min Range: -8.8410
Max Act: 8.5910. Min Act: -0.1700
Data Index: 5687739 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.8410. Min Range: -8.8410
Max Act: 8.5910. Min Act: -0.1700
Data Index: 3706005 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.8410. Min Range: -8.8410
Max Act: 8.5285. Min Act: -0.1700
Data Index: 5673319 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.8410. Min Range: -8.8410
Max Act: 8.5910. Min Act: -0.1700
Data Index: 4965535 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.8410. Min Range: -8.8410
Max Act: 8.5910. Min Act: -0.1700
Data Index: 1320833 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.8410. Min Range: -8.8410
Max Act: 8.5285. Min Act: -0.1700
Data Index: 2589447 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.8410. Min Range: -8.8410
Max Act: 8.5285. Min Act: -0.1700
Data Index: 2524803 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.8410. Min Range: -8.8410
Max Act: 8.5285. Min Act: -0.1700
Data Index: 1948917 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.8410. Min Range: -8.8410
Max Act: 8.5285. Min Act: -0.1700
Data Index: 4021915 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.8410. Min Range: -8.8410
Max Act: 8.5285. Min Act: -0.1700
Data Index: 2043002 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.8410. Min Range: -8.8410
Max Act: 8.5285. Min Act: -0.1700
Data Index: 1700052 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.8410. Min Range: -8.8410
Max Act: 8.5285. Min Act: -0.1700
Data Index: 5384327 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #19