Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2770 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1848. Min Range: -6.1848
Max Act: 6.1848. Min Act: -0.1700
Data Index: 8158041 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1848. Min Range: -6.1848
Max Act: 6.0285. Min Act: -0.1700
Data Index: 4504891 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1848. Min Range: -6.1848
Max Act: 5.9973. Min Act: -0.1700
Data Index: 6071640 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1848. Min Range: -6.1848
Max Act: 5.9660. Min Act: -0.1700
Data Index: 8607478 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1848. Min Range: -6.1848
Max Act: 5.9660. Min Act: -0.1700
Data Index: 7113423 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1848. Min Range: -6.1848
Max Act: 5.8410. Min Act: -0.1700
Data Index: 4961718 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1848. Min Range: -6.1848
Max Act: 5.8410. Min Act: -0.1700
Data Index: 4486493 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1848. Min Range: -6.1848
Max Act: 5.8098. Min Act: -0.1700
Data Index: 2341990 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1848. Min Range: -6.1848
Max Act: 5.7473. Min Act: -0.1700
Data Index: 2834794 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1848. Min Range: -6.1848
Max Act: 5.6848. Min Act: -0.1700
Data Index: 2245146 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1848. Min Range: -6.1848
Max Act: 5.6848. Min Act: -0.1700
Data Index: 7177275 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1848. Min Range: -6.1848
Max Act: 5.7160. Min Act: -0.1700
Data Index: 7398597 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1848. Min Range: -6.1848
Max Act: 5.6848. Min Act: -0.1700
Data Index: 552632 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1848. Min Range: -6.1848
Max Act: 5.6535. Min Act: -0.1700
Data Index: 2044006 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1848. Min Range: -6.1848
Max Act: 5.6535. Min Act: -0.1700
Data Index: 5750650 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1848. Min Range: -6.1848
Max Act: 5.6535. Min Act: -0.1700
Data Index: 8527222 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1848. Min Range: -6.1848
Max Act: 5.6535. Min Act: -0.1700
Data Index: 6471393 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1848. Min Range: -6.1848
Max Act: 5.6535. Min Act: -0.1700
Data Index: 667163 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1848. Min Range: -6.1848
Max Act: 5.6535. Min Act: -0.1700
Data Index: 1183931 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1848. Min Range: -6.1848
Max Act: 5.6223. Min Act: -0.1700
Data Index: 7211604 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #19