Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4913 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2376. Min Range: -6.2376
Max Act: 6.2376. Min Act: -0.1700
Data Index: 7261219 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2376. Min Range: -6.2376
Max Act: 5.9876. Min Act: -0.1700
Data Index: 111507 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2376. Min Range: -6.2376
Max Act: 5.9251. Min Act: -0.1700
Data Index: 5267244 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2376. Min Range: -6.2376
Max Act: 5.9251. Min Act: -0.1700
Data Index: 4698899 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2376. Min Range: -6.2376
Max Act: 5.9251. Min Act: -0.1700
Data Index: 598370 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2376. Min Range: -6.2376
Max Act: 5.8313. Min Act: -0.1700
Data Index: 7957931 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2376. Min Range: -6.2376
Max Act: 5.8626. Min Act: -0.1700
Data Index: 1676660 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2376. Min Range: -6.2376
Max Act: 5.8313. Min Act: -0.1700
Data Index: 8699105 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2376. Min Range: -6.2376
Max Act: 5.8313. Min Act: -0.1700
Data Index: 4797642 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2376. Min Range: -6.2376
Max Act: 5.8313. Min Act: -0.1700
Data Index: 1502599 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2376. Min Range: -6.2376
Max Act: 5.8001. Min Act: -0.1700
Data Index: 5905891 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2376. Min Range: -6.2376
Max Act: 5.8001. Min Act: -0.1700
Data Index: 7477720 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2376. Min Range: -6.2376
Max Act: 5.7688. Min Act: -0.1700
Data Index: 4731495 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2376. Min Range: -6.2376
Max Act: 5.7688. Min Act: -0.1700
Data Index: 2702871 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2376. Min Range: -6.2376
Max Act: 5.7376. Min Act: -0.1700
Data Index: 3770100 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2376. Min Range: -6.2376
Max Act: 5.7063. Min Act: -0.1700
Data Index: 3189003 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2376. Min Range: -6.2376
Max Act: 5.7063. Min Act: -0.1700
Data Index: 508634 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2376. Min Range: -6.2376
Max Act: 5.7063. Min Act: -0.1700
Data Index: 4194161 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2376. Min Range: -6.2376
Max Act: 5.7063. Min Act: -0.1700
Data Index: 3162350 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2376. Min Range: -6.2376
Max Act: 5.6438. Min Act: -0.1700
Data Index: 8374672 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #19