Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3237 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.2633. Min Range: -4.2633
Max Act: 4.2633. Min Act: -0.1700
Data Index: 4926993 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2633. Min Range: -4.2633
Max Act: 4.1696. Min Act: -0.1700
Data Index: 3931049 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2633. Min Range: -4.2633
Max Act: 4.2008. Min Act: -0.1700
Data Index: 3969367 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2633. Min Range: -4.2633
Max Act: 4.1383. Min Act: -0.1700
Data Index: 116826 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2633. Min Range: -4.2633
Max Act: 4.1383. Min Act: -0.1700
Data Index: 7691982 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2633. Min Range: -4.2633
Max Act: 4.1071. Min Act: -0.1700
Data Index: 7341182 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2633. Min Range: -4.2633
Max Act: 4.1071. Min Act: -0.1700
Data Index: 1591165 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2633. Min Range: -4.2633
Max Act: 4.1071. Min Act: -0.1700
Data Index: 2289249 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2633. Min Range: -4.2633
Max Act: 4.0758. Min Act: -0.1700
Data Index: 685456 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2633. Min Range: -4.2633
Max Act: 4.0758. Min Act: -0.1700
Data Index: 2724137 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2633. Min Range: -4.2633
Max Act: 4.0446. Min Act: -0.1700
Data Index: 6717433 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2633. Min Range: -4.2633
Max Act: 4.0446. Min Act: -0.1700
Data Index: 8352792 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2633. Min Range: -4.2633
Max Act: 4.0133. Min Act: -0.1700
Data Index: 892632 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2633. Min Range: -4.2633
Max Act: 3.9820. Min Act: -0.1700
Data Index: 8695454 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2633. Min Range: -4.2633
Max Act: 3.9820. Min Act: -0.1700
Data Index: 2266128 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2633. Min Range: -4.2633
Max Act: 3.9820. Min Act: -0.1700
Data Index: 2887973 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2633. Min Range: -4.2633
Max Act: 3.9508. Min Act: -0.1700
Data Index: 7075027 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2633. Min Range: -4.2633
Max Act: 3.9508. Min Act: -0.1700
Data Index: 3211575 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2633. Min Range: -4.2633
Max Act: 3.9508. Min Act: -0.1700
Data Index: 203738 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2633. Min Range: -4.2633
Max Act: 3.9508. Min Act: -0.1700
Data Index: 5582496 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #19