Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3884 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1888. Min Range: -8.1888
Max Act: 8.1888. Min Act: -0.1700
Data Index: 6414582 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1888. Min Range: -8.1888
Max Act: 8.1888. Min Act: -0.1700
Data Index: 1471418 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1888. Min Range: -8.1888
Max Act: 8.0951. Min Act: -0.1700
Data Index: 3648607 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1888. Min Range: -8.1888
Max Act: 7.8763. Min Act: -0.1700
Data Index: 5171053 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1888. Min Range: -8.1888
Max Act: 7.8451. Min Act: -0.1700
Data Index: 5044916 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1888. Min Range: -8.1888
Max Act: 7.7826. Min Act: -0.1700
Data Index: 5095290 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1888. Min Range: -8.1888
Max Act: 7.8138. Min Act: -0.1700
Data Index: 5239792 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1888. Min Range: -8.1888
Max Act: 7.7513. Min Act: -0.1700
Data Index: 1036311 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1888. Min Range: -8.1888
Max Act: 7.7826. Min Act: -0.1700
Data Index: 5447582 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1888. Min Range: -8.1888
Max Act: 7.6576. Min Act: -0.1700
Data Index: 4813344 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1888. Min Range: -8.1888
Max Act: 7.6888. Min Act: -0.1700
Data Index: 5180929 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1888. Min Range: -8.1888
Max Act: 7.6576. Min Act: -0.1700
Data Index: 2494384 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1888. Min Range: -8.1888
Max Act: 7.6888. Min Act: -0.1700
Data Index: 4240802 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1888. Min Range: -8.1888
Max Act: 7.6263. Min Act: -0.1700
Data Index: 259060 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1888. Min Range: -8.1888
Max Act: 7.6263. Min Act: -0.1700
Data Index: 7359340 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1888. Min Range: -8.1888
Max Act: 7.6888. Min Act: -0.1700
Data Index: 7972342 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1888. Min Range: -8.1888
Max Act: 7.6263. Min Act: -0.1700
Data Index: 2590833 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1888. Min Range: -8.1888
Max Act: 7.6576. Min Act: -0.1700
Data Index: 4841772 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1888. Min Range: -8.1888
Max Act: 7.5638. Min Act: -0.1700
Data Index: 3146974 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1888. Min Range: -8.1888
Max Act: 7.5638. Min Act: -0.1700
Data Index: 8059382 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #19