Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5305 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4509. Min Range: -8.4509
Max Act: 8.4509. Min Act: -0.1700
Data Index: 6288894 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4509. Min Range: -8.4509
Max Act: 8.3884. Min Act: -0.1700
Data Index: 290224 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4509. Min Range: -8.4509
Max Act: 8.1072. Min Act: -0.1700
Data Index: 8482802 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4509. Min Range: -8.4509
Max Act: 8.0447. Min Act: -0.1700
Data Index: 393645 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4509. Min Range: -8.4509
Max Act: 8.0134. Min Act: -0.1700
Data Index: 1385885 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4509. Min Range: -8.4509
Max Act: 7.9822. Min Act: -0.1700
Data Index: 8825015 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4509. Min Range: -8.4509
Max Act: 7.8884. Min Act: -0.1700
Data Index: 1086532 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4509. Min Range: -8.4509
Max Act: 7.8884. Min Act: -0.1700
Data Index: 6691624 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4509. Min Range: -8.4509
Max Act: 7.8572. Min Act: -0.1700
Data Index: 4604788 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4509. Min Range: -8.4509
Max Act: 7.8572. Min Act: -0.1700
Data Index: 8318561 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4509. Min Range: -8.4509
Max Act: 7.8259. Min Act: -0.1700
Data Index: 3169693 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4509. Min Range: -8.4509
Max Act: 7.8259. Min Act: -0.1700
Data Index: 6023376 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4509. Min Range: -8.4509
Max Act: 7.7947. Min Act: -0.1700
Data Index: 8443781 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4509. Min Range: -8.4509
Max Act: 7.7634. Min Act: -0.1700
Data Index: 5727679 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4509. Min Range: -8.4509
Max Act: 7.7009. Min Act: -0.1700
Data Index: 1587868 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4509. Min Range: -8.4509
Max Act: 7.6384. Min Act: -0.1700
Data Index: 6802274 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4509. Min Range: -8.4509
Max Act: 7.5447. Min Act: -0.1700
Data Index: 3856992 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4509. Min Range: -8.4509
Max Act: 7.5759. Min Act: -0.1700
Data Index: 3363823 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4509. Min Range: -8.4509
Max Act: 7.5447. Min Act: -0.1700
Data Index: 3179830 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4509. Min Range: -8.4509
Max Act: 7.5447. Min Act: -0.1700
Data Index: 5363596 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #19