Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 337 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2878. Min Range: -5.2878
Max Act: 5.2878. Min Act: -0.1700
Data Index: 8813763 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2878. Min Range: -5.2878
Max Act: 5.2565. Min Act: -0.1700
Data Index: 1356466 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2878. Min Range: -5.2878
Max Act: 5.2253. Min Act: -0.1700
Data Index: 6546788 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2878. Min Range: -5.2878
Max Act: 5.1940. Min Act: -0.1700
Data Index: 2771004 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2878. Min Range: -5.2878
Max Act: 5.1315. Min Act: -0.1700
Data Index: 4636947 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2878. Min Range: -5.2878
Max Act: 5.1315. Min Act: -0.1700
Data Index: 959516 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2878. Min Range: -5.2878
Max Act: 5.1003. Min Act: -0.1700
Data Index: 3894651 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2878. Min Range: -5.2878
Max Act: 5.1003. Min Act: -0.1700
Data Index: 2304964 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2878. Min Range: -5.2878
Max Act: 5.0690. Min Act: -0.1700
Data Index: 7689366 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2878. Min Range: -5.2878
Max Act: 5.0690. Min Act: -0.1700
Data Index: 3238737 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2878. Min Range: -5.2878
Max Act: 5.0378. Min Act: -0.1700
Data Index: 428133 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2878. Min Range: -5.2878
Max Act: 5.0065. Min Act: -0.1700
Data Index: 4787729 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2878. Min Range: -5.2878
Max Act: 5.0065. Min Act: -0.1700
Data Index: 5859014 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2878. Min Range: -5.2878
Max Act: 5.0065. Min Act: -0.1700
Data Index: 2369355 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2878. Min Range: -5.2878
Max Act: 5.0378. Min Act: -0.1700
Data Index: 7258830 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2878. Min Range: -5.2878
Max Act: 5.0065. Min Act: -0.1700
Data Index: 6654451 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2878. Min Range: -5.2878
Max Act: 4.9753. Min Act: -0.1700
Data Index: 3918594 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2878. Min Range: -5.2878
Max Act: 4.9753. Min Act: -0.1700
Data Index: 1848973 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2878. Min Range: -5.2878
Max Act: 4.9440. Min Act: -0.1700
Data Index: 7511328 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2878. Min Range: -5.2878
Max Act: 4.9440. Min Act: -0.1700
Data Index: 7530043 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #19