Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1631 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2169. Min Range: -8.2169
Max Act: 8.2169. Min Act: -0.1700
Data Index: 3040535 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2169. Min Range: -8.2169
Max Act: 8.2169. Min Act: -0.1700
Data Index: 5982004 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2169. Min Range: -8.2169
Max Act: 8.1544. Min Act: -0.1700
Data Index: 2309185 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2169. Min Range: -8.2169
Max Act: 8.1231. Min Act: -0.1700
Data Index: 2166257 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2169. Min Range: -8.2169
Max Act: 8.0606. Min Act: -0.1700
Data Index: 4843680 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2169. Min Range: -8.2169
Max Act: 7.9669. Min Act: -0.1700
Data Index: 839140 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2169. Min Range: -8.2169
Max Act: 7.8731. Min Act: -0.1700
Data Index: 5913487 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2169. Min Range: -8.2169
Max Act: 7.8419. Min Act: -0.1700
Data Index: 8005961 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2169. Min Range: -8.2169
Max Act: 7.7794. Min Act: -0.1700
Data Index: 4965651 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2169. Min Range: -8.2169
Max Act: 7.7794. Min Act: -0.1700
Data Index: 3440773 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2169. Min Range: -8.2169
Max Act: 7.8106. Min Act: -0.1700
Data Index: 7308869 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2169. Min Range: -8.2169
Max Act: 7.7481. Min Act: -0.1700
Data Index: 3440774 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2169. Min Range: -8.2169
Max Act: 7.7794. Min Act: -0.1700
Data Index: 2580154 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2169. Min Range: -8.2169
Max Act: 7.7481. Min Act: -0.1700
Data Index: 4903447 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2169. Min Range: -8.2169
Max Act: 7.7481. Min Act: -0.1700
Data Index: 1894209 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2169. Min Range: -8.2169
Max Act: 7.6856. Min Act: -0.1700
Data Index: 1129853 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2169. Min Range: -8.2169
Max Act: 7.6856. Min Act: -0.1700
Data Index: 3463408 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2169. Min Range: -8.2169
Max Act: 7.6856. Min Act: -0.1700
Data Index: 8625561 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2169. Min Range: -8.2169
Max Act: 7.6856. Min Act: -0.1700
Data Index: 4968751 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2169. Min Range: -8.2169
Max Act: 7.6544. Min Act: -0.1700
Data Index: 6206838 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #19