Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3790 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.0889. Min Range: -10.0889
Max Act: 10.0889. Min Act: -0.1700
Data Index: 515889 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.0889. Min Range: -10.0889
Max Act: 10.0889. Min Act: -0.1700
Data Index: 7979173 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.0889. Min Range: -10.0889
Max Act: 10.0889. Min Act: -0.1700
Data Index: 488927 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.0889. Min Range: -10.0889
Max Act: 9.7764. Min Act: -0.1700
Data Index: 4741628 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.0889. Min Range: -10.0889
Max Act: 9.7139. Min Act: -0.1700
Data Index: 4430808 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.0889. Min Range: -10.0889
Max Act: 9.7139. Min Act: -0.1700
Data Index: 1739950 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.0889. Min Range: -10.0889
Max Act: 9.6514. Min Act: -0.1700
Data Index: 7768197 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.0889. Min Range: -10.0889
Max Act: 9.5889. Min Act: -0.1700
Data Index: 1100501 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.0889. Min Range: -10.0889
Max Act: 9.5264. Min Act: -0.1700
Data Index: 6988260 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.0889. Min Range: -10.0889
Max Act: 9.5264. Min Act: -0.1700
Data Index: 2304139 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.0889. Min Range: -10.0889
Max Act: 9.4014. Min Act: -0.1700
Data Index: 5581694 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.0889. Min Range: -10.0889
Max Act: 9.4639. Min Act: -0.1700
Data Index: 8462443 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.0889. Min Range: -10.0889
Max Act: 9.4014. Min Act: -0.1700
Data Index: 1681971 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.0889. Min Range: -10.0889
Max Act: 9.4014. Min Act: -0.1700
Data Index: 6929394 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.0889. Min Range: -10.0889
Max Act: 9.3389. Min Act: -0.1700
Data Index: 966513 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.0889. Min Range: -10.0889
Max Act: 9.3389. Min Act: -0.1700
Data Index: 6483825 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.0889. Min Range: -10.0889
Max Act: 9.3389. Min Act: -0.1700
Data Index: 8143527 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.0889. Min Range: -10.0889
Max Act: 9.3389. Min Act: -0.1700
Data Index: 6162770 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.0889. Min Range: -10.0889
Max Act: 9.3389. Min Act: -0.1700
Data Index: 4979633 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.0889. Min Range: -10.0889
Max Act: 9.2764. Min Act: -0.1700
Data Index: 6581944 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #19