Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4506 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7009. Min Range: -6.7009
Max Act: 6.7009. Min Act: -0.1700
Data Index: 1158621 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7009. Min Range: -6.7009
Max Act: 6.4196. Min Act: -0.1700
Data Index: 7169587 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7009. Min Range: -6.7009
Max Act: 6.3884. Min Act: -0.1700
Data Index: 139642 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7009. Min Range: -6.7009
Max Act: 6.3571. Min Act: -0.1700
Data Index: 5508396 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7009. Min Range: -6.7009
Max Act: 6.2946. Min Act: -0.1700
Data Index: 291146 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7009. Min Range: -6.7009
Max Act: 6.2946. Min Act: -0.1700
Data Index: 7383811 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7009. Min Range: -6.7009
Max Act: 6.2321. Min Act: -0.1700
Data Index: 4985514 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7009. Min Range: -6.7009
Max Act: 6.2321. Min Act: -0.1700
Data Index: 7730754 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7009. Min Range: -6.7009
Max Act: 6.2009. Min Act: -0.1700
Data Index: 2874008 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7009. Min Range: -6.7009
Max Act: 6.1384. Min Act: -0.1700
Data Index: 7222385 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7009. Min Range: -6.7009
Max Act: 6.1384. Min Act: -0.1700
Data Index: 6182573 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7009. Min Range: -6.7009
Max Act: 6.0446. Min Act: -0.1700
Data Index: 7040784 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7009. Min Range: -6.7009
Max Act: 6.0759. Min Act: -0.1700
Data Index: 241661 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7009. Min Range: -6.7009
Max Act: 6.0134. Min Act: -0.1700
Data Index: 1437871 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7009. Min Range: -6.7009
Max Act: 6.0134. Min Act: -0.1700
Data Index: 388794 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7009. Min Range: -6.7009
Max Act: 6.0446. Min Act: -0.1700
Data Index: 1086841 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7009. Min Range: -6.7009
Max Act: 6.0134. Min Act: -0.1700
Data Index: 7164957 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7009. Min Range: -6.7009
Max Act: 6.0134. Min Act: -0.1700
Data Index: 7240598 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7009. Min Range: -6.7009
Max Act: 5.9821. Min Act: -0.1700
Data Index: 6993638 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7009. Min Range: -6.7009
Max Act: 5.9196. Min Act: -0.1700
Data Index: 4904975 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #19