Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5278 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.6611. Min Range: -9.6611
Max Act: 9.6611. Min Act: -0.1700
Data Index: 3472989 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.6611. Min Range: -9.6611
Max Act: 9.5361. Min Act: -0.1700
Data Index: 4198954 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.6611. Min Range: -9.6611
Max Act: 9.5361. Min Act: -0.1700
Data Index: 5156418 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.6611. Min Range: -9.6611
Max Act: 9.5361. Min Act: -0.1700
Data Index: 2568005 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.6611. Min Range: -9.6611
Max Act: 9.4736. Min Act: -0.1700
Data Index: 7850107 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.6611. Min Range: -9.6611
Max Act: 9.3486. Min Act: -0.1700
Data Index: 1601841 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.6611. Min Range: -9.6611
Max Act: 9.3486. Min Act: -0.1700
Data Index: 6389417 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.6611. Min Range: -9.6611
Max Act: 9.1611. Min Act: -0.1700
Data Index: 5674426 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.6611. Min Range: -9.6611
Max Act: 9.0986. Min Act: -0.1700
Data Index: 7844673 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.6611. Min Range: -9.6611
Max Act: 9.0986. Min Act: -0.1700
Data Index: 6719396 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.6611. Min Range: -9.6611
Max Act: 9.0361. Min Act: -0.1700
Data Index: 8520956 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.6611. Min Range: -9.6611
Max Act: 9.0361. Min Act: -0.1700
Data Index: 5256223 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.6611. Min Range: -9.6611
Max Act: 9.0361. Min Act: -0.1700
Data Index: 2083414 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.6611. Min Range: -9.6611
Max Act: 9.0361. Min Act: -0.1700
Data Index: 6783880 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.6611. Min Range: -9.6611
Max Act: 9.0361. Min Act: -0.1700
Data Index: 7555978 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.6611. Min Range: -9.6611
Max Act: 8.9736. Min Act: -0.1700
Data Index: 6325990 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.6611. Min Range: -9.6611
Max Act: 8.9736. Min Act: -0.1700
Data Index: 3110574 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.6611. Min Range: -9.6611
Max Act: 8.9736. Min Act: -0.1700
Data Index: 5118631 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.6611. Min Range: -9.6611
Max Act: 8.9736. Min Act: -0.1700
Data Index: 2734819 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.6611. Min Range: -9.6611
Max Act: 8.9736. Min Act: -0.1700
Data Index: 6243990 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #19