Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2784 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6784. Min Range: -6.6784
Max Act: 6.6784. Min Act: -0.1700
Data Index: 3790309 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6784. Min Range: -6.6784
Max Act: 6.5222. Min Act: -0.1700
Data Index: 3927649 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6784. Min Range: -6.6784
Max Act: 6.2722. Min Act: -0.1700
Data Index: 8397492 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6784. Min Range: -6.6784
Max Act: 6.1784. Min Act: -0.1700
Data Index: 1558381 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6784. Min Range: -6.6784
Max Act: 6.1784. Min Act: -0.1700
Data Index: 8247000 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6784. Min Range: -6.6784
Max Act: 6.1784. Min Act: -0.1700
Data Index: 4494122 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6784. Min Range: -6.6784
Max Act: 6.0847. Min Act: -0.1700
Data Index: 8098143 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6784. Min Range: -6.6784
Max Act: 6.0534. Min Act: -0.1700
Data Index: 3570437 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6784. Min Range: -6.6784
Max Act: 6.0534. Min Act: -0.1700
Data Index: 4087764 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6784. Min Range: -6.6784
Max Act: 6.0847. Min Act: -0.1700
Data Index: 1061176 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6784. Min Range: -6.6784
Max Act: 6.0534. Min Act: -0.1700
Data Index: 400815 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6784. Min Range: -6.6784
Max Act: 6.0222. Min Act: -0.1700
Data Index: 3966065 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6784. Min Range: -6.6784
Max Act: 6.0534. Min Act: -0.1700
Data Index: 6109916 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6784. Min Range: -6.6784
Max Act: 6.0222. Min Act: -0.1700
Data Index: 4679047 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6784. Min Range: -6.6784
Max Act: 6.0222. Min Act: -0.1700
Data Index: 7499904 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6784. Min Range: -6.6784
Max Act: 6.0222. Min Act: -0.1700
Data Index: 813541 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6784. Min Range: -6.6784
Max Act: 6.0222. Min Act: -0.1700
Data Index: 3570438 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6784. Min Range: -6.6784
Max Act: 5.9909. Min Act: -0.1700
Data Index: 4239720 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6784. Min Range: -6.6784
Max Act: 5.9909. Min Act: -0.1700
Data Index: 687302 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6784. Min Range: -6.6784
Max Act: 5.9909. Min Act: -0.1700
Data Index: 5968591 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #19