Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3189 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.4926. Min Range: -10.4926
Max Act: 10.4926. Min Act: -0.1700
Data Index: 3753680 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.4926. Min Range: -10.4926
Max Act: 10.3676. Min Act: -0.1700
Data Index: 7500016 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.4926. Min Range: -10.4926
Max Act: 10.1176. Min Act: -0.1700
Data Index: 6131704 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.4926. Min Range: -10.4926
Max Act: 9.8676. Min Act: -0.1700
Data Index: 6131701 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.4926. Min Range: -10.4926
Max Act: 9.8676. Min Act: -0.1700
Data Index: 3584675 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.4926. Min Range: -10.4926
Max Act: 9.8676. Min Act: -0.1700
Data Index: 8093812 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.4926. Min Range: -10.4926
Max Act: 9.8051. Min Act: -0.1700
Data Index: 7024380 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.4926. Min Range: -10.4926
Max Act: 9.8051. Min Act: -0.1700
Data Index: 8617679 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.4926. Min Range: -10.4926
Max Act: 9.8051. Min Act: -0.1700
Data Index: 3764555 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.4926. Min Range: -10.4926
Max Act: 9.7426. Min Act: -0.1700
Data Index: 6131702 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.4926. Min Range: -10.4926
Max Act: 9.6801. Min Act: -0.1700
Data Index: 8681008 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.4926. Min Range: -10.4926
Max Act: 9.6801. Min Act: -0.1700
Data Index: 1689640 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.4926. Min Range: -10.4926
Max Act: 9.6801. Min Act: -0.1700
Data Index: 5229907 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.4926. Min Range: -10.4926
Max Act: 9.6176. Min Act: -0.1700
Data Index: 7326101 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.4926. Min Range: -10.4926
Max Act: 9.6801. Min Act: -0.1700
Data Index: 8093813 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.4926. Min Range: -10.4926
Max Act: 9.6176. Min Act: -0.1700
Data Index: 6138984 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.4926. Min Range: -10.4926
Max Act: 9.6176. Min Act: -0.1700
Data Index: 3889561 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.4926. Min Range: -10.4926
Max Act: 9.6176. Min Act: -0.1700
Data Index: 6242713 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.4926. Min Range: -10.4926
Max Act: 9.6176. Min Act: -0.1700
Data Index: 3340144 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.4926. Min Range: -10.4926
Max Act: 9.5551. Min Act: -0.1700
Data Index: 2743120 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #19