Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4776 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1066. Min Range: -8.1066
Max Act: 8.1066. Min Act: -0.1700
Data Index: 7761362 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1066. Min Range: -8.1066
Max Act: 8.1066. Min Act: -0.1700
Data Index: 5084425 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1066. Min Range: -8.1066
Max Act: 7.8566. Min Act: -0.1700
Data Index: 6602763 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1066. Min Range: -8.1066
Max Act: 7.7629. Min Act: -0.1700
Data Index: 5402652 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1066. Min Range: -8.1066
Max Act: 7.7629. Min Act: -0.1700
Data Index: 5051693 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1066. Min Range: -8.1066
Max Act: 7.7316. Min Act: -0.1700
Data Index: 1581087 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1066. Min Range: -8.1066
Max Act: 7.7316. Min Act: -0.1700
Data Index: 2462669 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1066. Min Range: -8.1066
Max Act: 7.6691. Min Act: -0.1700
Data Index: 5218887 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1066. Min Range: -8.1066
Max Act: 7.6379. Min Act: -0.1700
Data Index: 2320892 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1066. Min Range: -8.1066
Max Act: 7.6379. Min Act: -0.1700
Data Index: 1869591 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1066. Min Range: -8.1066
Max Act: 7.6066. Min Act: -0.1700
Data Index: 1366857 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1066. Min Range: -8.1066
Max Act: 7.6066. Min Act: -0.1700
Data Index: 7210959 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1066. Min Range: -8.1066
Max Act: 7.5754. Min Act: -0.1700
Data Index: 8658739 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1066. Min Range: -8.1066
Max Act: 7.5754. Min Act: -0.1700
Data Index: 5203932 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1066. Min Range: -8.1066
Max Act: 7.5754. Min Act: -0.1700
Data Index: 7103943 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1066. Min Range: -8.1066
Max Act: 7.5129. Min Act: -0.1700
Data Index: 6411897 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1066. Min Range: -8.1066
Max Act: 7.5129. Min Act: -0.1700
Data Index: 6451830 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1066. Min Range: -8.1066
Max Act: 7.4816. Min Act: -0.1700
Data Index: 3523213 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1066. Min Range: -8.1066
Max Act: 7.4504. Min Act: -0.1700
Data Index: 3701551 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1066. Min Range: -8.1066
Max Act: 7.4816. Min Act: -0.1700
Data Index: 6283022 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #19