Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1950 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.5169. Min Range: -9.5169
Max Act: 9.5169. Min Act: -0.1700
Data Index: 1734578 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.5169. Min Range: -9.5169
Max Act: 8.8919. Min Act: -0.1700
Data Index: 2174616 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.5169. Min Range: -9.5169
Max Act: 8.8294. Min Act: -0.1700
Data Index: 5078665 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.5169. Min Range: -9.5169
Max Act: 8.8294. Min Act: -0.1700
Data Index: 5638626 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.5169. Min Range: -9.5169
Max Act: 8.7669. Min Act: -0.1700
Data Index: 3644735 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.5169. Min Range: -9.5169
Max Act: 8.7669. Min Act: -0.1700
Data Index: 4201037 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.5169. Min Range: -9.5169
Max Act: 8.7669. Min Act: -0.1700
Data Index: 6191477 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.5169. Min Range: -9.5169
Max Act: 8.6419. Min Act: -0.1700
Data Index: 7694787 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.5169. Min Range: -9.5169
Max Act: 8.5794. Min Act: -0.1700
Data Index: 5111828 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.5169. Min Range: -9.5169
Max Act: 8.5794. Min Act: -0.1700
Data Index: 802668 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.5169. Min Range: -9.5169
Max Act: 8.4544. Min Act: -0.1700
Data Index: 3443732 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.5169. Min Range: -9.5169
Max Act: 8.4544. Min Act: -0.1700
Data Index: 2838587 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.5169. Min Range: -9.5169
Max Act: 8.3919. Min Act: -0.1700
Data Index: 6281336 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.5169. Min Range: -9.5169
Max Act: 8.3294. Min Act: -0.1700
Data Index: 127223 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.5169. Min Range: -9.5169
Max Act: 8.3294. Min Act: -0.1700
Data Index: 1232423 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.5169. Min Range: -9.5169
Max Act: 8.3294. Min Act: -0.1700
Data Index: 7607956 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.5169. Min Range: -9.5169
Max Act: 8.2044. Min Act: -0.1700
Data Index: 8740087 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.5169. Min Range: -9.5169
Max Act: 8.2669. Min Act: -0.1700
Data Index: 8184135 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.5169. Min Range: -9.5169
Max Act: 8.2044. Min Act: -0.1700
Data Index: 7480623 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.5169. Min Range: -9.5169
Max Act: 8.2044. Min Act: -0.1700
Data Index: 39876 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #19