Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1812 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9061. Min Range: -7.9061
Max Act: 7.9061. Min Act: -0.1700
Data Index: 2413915 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9061. Min Range: -7.9061
Max Act: 7.4999. Min Act: -0.1700
Data Index: 2695417 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9061. Min Range: -7.9061
Max Act: 7.1874. Min Act: -0.1700
Data Index: 5104284 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9061. Min Range: -7.9061
Max Act: 7.1874. Min Act: -0.1700
Data Index: 5984057 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9061. Min Range: -7.9061
Max Act: 7.1874. Min Act: -0.1700
Data Index: 8473501 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9061. Min Range: -7.9061
Max Act: 7.1561. Min Act: -0.1700
Data Index: 705686 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9061. Min Range: -7.9061
Max Act: 7.1249. Min Act: -0.1700
Data Index: 661224 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9061. Min Range: -7.9061
Max Act: 7.1249. Min Act: -0.1700
Data Index: 2471242 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9061. Min Range: -7.9061
Max Act: 7.0936. Min Act: -0.1700
Data Index: 4591486 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9061. Min Range: -7.9061
Max Act: 6.9999. Min Act: -0.1700
Data Index: 942689 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9061. Min Range: -7.9061
Max Act: 6.9999. Min Act: -0.1700
Data Index: 7240053 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9061. Min Range: -7.9061
Max Act: 6.9999. Min Act: -0.1700
Data Index: 2740922 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9061. Min Range: -7.9061
Max Act: 6.9686. Min Act: -0.1700
Data Index: 4917750 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9061. Min Range: -7.9061
Max Act: 6.9374. Min Act: -0.1700
Data Index: 6385260 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9061. Min Range: -7.9061
Max Act: 6.9061. Min Act: -0.1700
Data Index: 6595390 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9061. Min Range: -7.9061
Max Act: 6.8749. Min Act: -0.1700
Data Index: 7381592 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9061. Min Range: -7.9061
Max Act: 6.8749. Min Act: -0.1700
Data Index: 2811356 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9061. Min Range: -7.9061
Max Act: 6.9061. Min Act: -0.1700
Data Index: 1703727 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9061. Min Range: -7.9061
Max Act: 6.8749. Min Act: -0.1700
Data Index: 6069117 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9061. Min Range: -7.9061
Max Act: 6.8436. Min Act: -0.1700
Data Index: 2934018 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #19