Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3576 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8010. Min Range: -4.8010
Max Act: 4.8010. Min Act: -0.1700
Data Index: 882876 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8010. Min Range: -4.8010
Max Act: 4.8010. Min Act: -0.1700
Data Index: 1819217 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8010. Min Range: -4.8010
Max Act: 4.7072. Min Act: -0.1700
Data Index: 5605617 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8010. Min Range: -4.8010
Max Act: 4.6760. Min Act: -0.1700
Data Index: 5188633 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8010. Min Range: -4.8010
Max Act: 4.6447. Min Act: -0.1700
Data Index: 1917968 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8010. Min Range: -4.8010
Max Act: 4.6135. Min Act: -0.1700
Data Index: 7749064 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8010. Min Range: -4.8010
Max Act: 4.6135. Min Act: -0.1700
Data Index: 1390308 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8010. Min Range: -4.8010
Max Act: 4.6135. Min Act: -0.1700
Data Index: 6861694 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8010. Min Range: -4.8010
Max Act: 4.5822. Min Act: -0.1700
Data Index: 6695853 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8010. Min Range: -4.8010
Max Act: 4.5822. Min Act: -0.1700
Data Index: 8247181 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8010. Min Range: -4.8010
Max Act: 4.5822. Min Act: -0.1700
Data Index: 430735 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8010. Min Range: -4.8010
Max Act: 4.5822. Min Act: -0.1700
Data Index: 6853010 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8010. Min Range: -4.8010
Max Act: 4.5822. Min Act: -0.1700
Data Index: 3394953 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8010. Min Range: -4.8010
Max Act: 4.5510. Min Act: -0.1700
Data Index: 2015395 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8010. Min Range: -4.8010
Max Act: 4.5510. Min Act: -0.1700
Data Index: 8017088 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8010. Min Range: -4.8010
Max Act: 4.5510. Min Act: -0.1700
Data Index: 2028779 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8010. Min Range: -4.8010
Max Act: 4.5197. Min Act: -0.1700
Data Index: 8147210 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8010. Min Range: -4.8010
Max Act: 4.5510. Min Act: -0.1700
Data Index: 8263318 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8010. Min Range: -4.8010
Max Act: 4.5197. Min Act: -0.1700
Data Index: 5791854 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8010. Min Range: -4.8010
Max Act: 4.5197. Min Act: -0.1700
Data Index: 5842374 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #19