Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4706 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.0388. Min Range: -9.0388
Max Act: 9.0388. Min Act: -0.1700
Data Index: 8090116 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.0388. Min Range: -9.0388
Max Act: 9.0388. Min Act: -0.1700
Data Index: 1803568 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.0388. Min Range: -9.0388
Max Act: 9.0388. Min Act: -0.1700
Data Index: 6809405 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.0388. Min Range: -9.0388
Max Act: 8.9138. Min Act: -0.1700
Data Index: 5405958 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.0388. Min Range: -9.0388
Max Act: 8.8513. Min Act: -0.1700
Data Index: 7142968 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.0388. Min Range: -9.0388
Max Act: 8.7888. Min Act: -0.1700
Data Index: 6321078 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.0388. Min Range: -9.0388
Max Act: 8.7888. Min Act: -0.1700
Data Index: 1450953 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.0388. Min Range: -9.0388
Max Act: 8.7888. Min Act: -0.1700
Data Index: 5012856 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.0388. Min Range: -9.0388
Max Act: 8.7888. Min Act: -0.1700
Data Index: 3812939 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.0388. Min Range: -9.0388
Max Act: 8.7263. Min Act: -0.1700
Data Index: 5419759 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.0388. Min Range: -9.0388
Max Act: 8.7263. Min Act: -0.1700
Data Index: 5634982 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.0388. Min Range: -9.0388
Max Act: 8.6638. Min Act: -0.1700
Data Index: 1356426 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.0388. Min Range: -9.0388
Max Act: 8.6638. Min Act: -0.1700
Data Index: 2563757 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.0388. Min Range: -9.0388
Max Act: 8.6013. Min Act: -0.1700
Data Index: 1072346 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.0388. Min Range: -9.0388
Max Act: 8.6013. Min Act: -0.1700
Data Index: 6973559 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.0388. Min Range: -9.0388
Max Act: 8.6013. Min Act: -0.1700
Data Index: 3474116 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.0388. Min Range: -9.0388
Max Act: 8.6013. Min Act: -0.1700
Data Index: 3982947 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.0388. Min Range: -9.0388
Max Act: 8.5388. Min Act: -0.1700
Data Index: 3813679 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.0388. Min Range: -9.0388
Max Act: 8.5388. Min Act: -0.1700
Data Index: 6807520 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.0388. Min Range: -9.0388
Max Act: 8.4763. Min Act: -0.1700
Data Index: 4267329 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #19