Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 783 in Layer 41
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2644. Min Range: -8.2644
Max Act: 8.2644. Min Act: -0.1700
Data Index: 4786540 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2644. Min Range: -8.2644
Max Act: 8.1394. Min Act: -0.1700
Data Index: 4166713 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2644. Min Range: -8.2644
Max Act: 8.2019. Min Act: -0.1700
Data Index: 746247 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2644. Min Range: -8.2644
Max Act: 7.9519. Min Act: -0.1700
Data Index: 1713110 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2644. Min Range: -8.2644
Max Act: 7.8894. Min Act: -0.1700
Data Index: 8054699 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2644. Min Range: -8.2644
Max Act: 8.0144. Min Act: -0.1700
Data Index: 5020614 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2644. Min Range: -8.2644
Max Act: 7.8894. Min Act: -0.1700
Data Index: 656115 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2644. Min Range: -8.2644
Max Act: 7.7332. Min Act: -0.1700
Data Index: 6138504 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2644. Min Range: -8.2644
Max Act: 7.7019. Min Act: -0.1700
Data Index: 871547 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2644. Min Range: -8.2644
Max Act: 7.6707. Min Act: -0.1700
Data Index: 4714212 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2644. Min Range: -8.2644
Max Act: 7.6394. Min Act: -0.1700
Data Index: 3362097 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2644. Min Range: -8.2644
Max Act: 7.6707. Min Act: -0.1700
Data Index: 2916727 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2644. Min Range: -8.2644
Max Act: 7.6082. Min Act: -0.1700
Data Index: 8092310 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2644. Min Range: -8.2644
Max Act: 7.5769. Min Act: -0.1700
Data Index: 5722112 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2644. Min Range: -8.2644
Max Act: 7.6082. Min Act: -0.1700
Data Index: 4147005 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2644. Min Range: -8.2644
Max Act: 7.5769. Min Act: -0.1700
Data Index: 6739471 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2644. Min Range: -8.2644
Max Act: 7.5769. Min Act: -0.1700
Data Index: 3136331 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2644. Min Range: -8.2644
Max Act: 7.5769. Min Act: -0.1700
Data Index: 6793061 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2644. Min Range: -8.2644
Max Act: 7.5769. Min Act: -0.1700
Data Index: 5622884 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2644. Min Range: -8.2644
Max Act: 7.5144. Min Act: -0.1700
Data Index: 4412764 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #19