Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3673 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5809. Min Range: -5.5809
Max Act: 5.5809. Min Act: -0.1700
Data Index: 8417779 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5809. Min Range: -5.5809
Max Act: 5.5496. Min Act: -0.1700
Data Index: 8731363 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5809. Min Range: -5.5809
Max Act: 5.3934. Min Act: -0.1700
Data Index: 6327874 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5809. Min Range: -5.5809
Max Act: 5.3934. Min Act: -0.1700
Data Index: 1236646 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5809. Min Range: -5.5809
Max Act: 5.3934. Min Act: -0.1700
Data Index: 6326804 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5809. Min Range: -5.5809
Max Act: 5.3309. Min Act: -0.1700
Data Index: 5232777 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5809. Min Range: -5.5809
Max Act: 5.3621. Min Act: -0.1700
Data Index: 7371153 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5809. Min Range: -5.5809
Max Act: 5.2996. Min Act: -0.1700
Data Index: 7935170 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5809. Min Range: -5.5809
Max Act: 5.3309. Min Act: -0.1700
Data Index: 174443 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5809. Min Range: -5.5809
Max Act: 5.2996. Min Act: -0.1700
Data Index: 4944284 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5809. Min Range: -5.5809
Max Act: 5.2684. Min Act: -0.1700
Data Index: 986536 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5809. Min Range: -5.5809
Max Act: 5.2059. Min Act: -0.1700
Data Index: 284910 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5809. Min Range: -5.5809
Max Act: 5.1746. Min Act: -0.1700
Data Index: 475782 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5809. Min Range: -5.5809
Max Act: 5.1746. Min Act: -0.1700
Data Index: 728845 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5809. Min Range: -5.5809
Max Act: 5.1434. Min Act: -0.1700
Data Index: 4900509 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5809. Min Range: -5.5809
Max Act: 5.1434. Min Act: -0.1700
Data Index: 8471085 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5809. Min Range: -5.5809
Max Act: 5.1434. Min Act: -0.1700
Data Index: 7181564 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5809. Min Range: -5.5809
Max Act: 5.1121. Min Act: -0.1700
Data Index: 363645 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5809. Min Range: -5.5809
Max Act: 5.1121. Min Act: -0.1700
Data Index: 6122240 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5809. Min Range: -5.5809
Max Act: 5.0496. Min Act: -0.1700
Data Index: 6959044 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #19