Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2860 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3353. Min Range: -8.3353
Max Act: 8.3353. Min Act: -0.1700
Data Index: 8475663 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3353. Min Range: -8.3353
Max Act: 8.3353. Min Act: -0.1700
Data Index: 771262 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3353. Min Range: -8.3353
Max Act: 8.2728. Min Act: -0.1700
Data Index: 5155240 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3353. Min Range: -8.3353
Max Act: 8.2103. Min Act: -0.1700
Data Index: 3545489 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3353. Min Range: -8.3353
Max Act: 8.2103. Min Act: -0.1700
Data Index: 127041 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3353. Min Range: -8.3353
Max Act: 8.1478. Min Act: -0.1700
Data Index: 301401 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3353. Min Range: -8.3353
Max Act: 8.1478. Min Act: -0.1700
Data Index: 4476011 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3353. Min Range: -8.3353
Max Act: 8.1478. Min Act: -0.1700
Data Index: 2364723 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3353. Min Range: -8.3353
Max Act: 8.0228. Min Act: -0.1700
Data Index: 7974817 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3353. Min Range: -8.3353
Max Act: 8.0228. Min Act: -0.1700
Data Index: 5021342 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3353. Min Range: -8.3353
Max Act: 7.9603. Min Act: -0.1700
Data Index: 7291281 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3353. Min Range: -8.3353
Max Act: 7.8978. Min Act: -0.1700
Data Index: 3939264 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3353. Min Range: -8.3353
Max Act: 7.8978. Min Act: -0.1700
Data Index: 816787 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3353. Min Range: -8.3353
Max Act: 7.8978. Min Act: -0.1700
Data Index: 6595784 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3353. Min Range: -8.3353
Max Act: 7.8353. Min Act: -0.1700
Data Index: 1603699 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3353. Min Range: -8.3353
Max Act: 7.8353. Min Act: -0.1700
Data Index: 3533006 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3353. Min Range: -8.3353
Max Act: 7.8353. Min Act: -0.1700
Data Index: 1851275 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3353. Min Range: -8.3353
Max Act: 7.8041. Min Act: -0.1700
Data Index: 7759150 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3353. Min Range: -8.3353
Max Act: 7.8353. Min Act: -0.1700
Data Index: 3468261 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3353. Min Range: -8.3353
Max Act: 7.8041. Min Act: -0.1700
Data Index: 6968451 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #19