Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2758 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.8035. Min Range: -9.8035
Max Act: 9.8035. Min Act: -0.1700
Data Index: 8581505 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.8035. Min Range: -9.8035
Max Act: 9.3660. Min Act: -0.1700
Data Index: 6972556 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.8035. Min Range: -9.8035
Max Act: 8.9910. Min Act: -0.1700
Data Index: 6855713 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.8035. Min Range: -9.8035
Max Act: 8.9910. Min Act: -0.1700
Data Index: 3199271 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.8035. Min Range: -9.8035
Max Act: 8.9285. Min Act: -0.1700
Data Index: 5120150 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.8035. Min Range: -9.8035
Max Act: 8.8660. Min Act: -0.1700
Data Index: 1025830 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.8035. Min Range: -9.8035
Max Act: 8.8035. Min Act: -0.1700
Data Index: 634749 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.8035. Min Range: -9.8035
Max Act: 8.8035. Min Act: -0.1700
Data Index: 7432624 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.8035. Min Range: -9.8035
Max Act: 8.8035. Min Act: -0.1700
Data Index: 907208 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.8035. Min Range: -9.8035
Max Act: 8.8035. Min Act: -0.1700
Data Index: 8187833 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.8035. Min Range: -9.8035
Max Act: 8.8035. Min Act: -0.1700
Data Index: 7864420 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.8035. Min Range: -9.8035
Max Act: 8.7410. Min Act: -0.1700
Data Index: 4142825 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.8035. Min Range: -9.8035
Max Act: 8.6785. Min Act: -0.1700
Data Index: 7175324 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.8035. Min Range: -9.8035
Max Act: 8.7410. Min Act: -0.1700
Data Index: 177451 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.8035. Min Range: -9.8035
Max Act: 8.7410. Min Act: -0.1700
Data Index: 5609438 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.8035. Min Range: -9.8035
Max Act: 8.7410. Min Act: -0.1700
Data Index: 3641950 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.8035. Min Range: -9.8035
Max Act: 8.6785. Min Act: -0.1700
Data Index: 3606159 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.8035. Min Range: -9.8035
Max Act: 8.6785. Min Act: -0.1700
Data Index: 8346504 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.8035. Min Range: -9.8035
Max Act: 8.6785. Min Act: -0.1700
Data Index: 2194850 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.8035. Min Range: -9.8035
Max Act: 8.6785. Min Act: -0.1700
Data Index: 4216598 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #19