Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1947 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4779. Min Range: -5.4779
Max Act: 5.4779. Min Act: -0.1700
Data Index: 2309094 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4779. Min Range: -5.4779
Max Act: 5.4779. Min Act: -0.1700
Data Index: 6088263 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4779. Min Range: -5.4779
Max Act: 5.2591. Min Act: -0.1700
Data Index: 2481263 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4779. Min Range: -5.4779
Max Act: 5.2591. Min Act: -0.1700
Data Index: 3652427 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4779. Min Range: -5.4779
Max Act: 5.2591. Min Act: -0.1700
Data Index: 4291325 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4779. Min Range: -5.4779
Max Act: 5.1966. Min Act: -0.1700
Data Index: 5625233 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4779. Min Range: -5.4779
Max Act: 5.2279. Min Act: -0.1700
Data Index: 950832 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4779. Min Range: -5.4779
Max Act: 5.1654. Min Act: -0.1700
Data Index: 1429889 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4779. Min Range: -5.4779
Max Act: 5.1654. Min Act: -0.1700
Data Index: 4839080 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4779. Min Range: -5.4779
Max Act: 5.1341. Min Act: -0.1700
Data Index: 1948181 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4779. Min Range: -5.4779
Max Act: 5.1341. Min Act: -0.1700
Data Index: 882432 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4779. Min Range: -5.4779
Max Act: 5.1029. Min Act: -0.1700
Data Index: 5118391 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4779. Min Range: -5.4779
Max Act: 5.0716. Min Act: -0.1700
Data Index: 4882927 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4779. Min Range: -5.4779
Max Act: 5.0716. Min Act: -0.1700
Data Index: 6200265 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4779. Min Range: -5.4779
Max Act: 5.0404. Min Act: -0.1700
Data Index: 3051503 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4779. Min Range: -5.4779
Max Act: 5.0404. Min Act: -0.1700
Data Index: 8220645 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4779. Min Range: -5.4779
Max Act: 5.0091. Min Act: -0.1700
Data Index: 6548369 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4779. Min Range: -5.4779
Max Act: 5.0091. Min Act: -0.1700
Data Index: 814267 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4779. Min Range: -5.4779
Max Act: 5.0091. Min Act: -0.1700
Data Index: 234975 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4779. Min Range: -5.4779
Max Act: 5.0091. Min Act: -0.1700
Data Index: 4588368 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #19