Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3516 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9200. Min Range: -3.9200
Max Act: 3.9200. Min Act: -0.1700
Data Index: 7825130 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9200. Min Range: -3.9200
Max Act: 3.8574. Min Act: -0.1700
Data Index: 6027033 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9200. Min Range: -3.9200
Max Act: 3.8574. Min Act: -0.1700
Data Index: 5087266 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9200. Min Range: -3.9200
Max Act: 3.8887. Min Act: -0.1700
Data Index: 1326095 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9200. Min Range: -3.9200
Max Act: 3.8262. Min Act: -0.1700
Data Index: 5938072 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9200. Min Range: -3.9200
Max Act: 3.7949. Min Act: -0.1700
Data Index: 4833881 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9200. Min Range: -3.9200
Max Act: 3.8262. Min Act: -0.1700
Data Index: 6879001 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9200. Min Range: -3.9200
Max Act: 3.8262. Min Act: -0.1700
Data Index: 8317683 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9200. Min Range: -3.9200
Max Act: 3.7636. Min Act: -0.1700
Data Index: 179613 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9200. Min Range: -3.9200
Max Act: 3.7949. Min Act: -0.1700
Data Index: 251892 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9200. Min Range: -3.9200
Max Act: 3.7636. Min Act: -0.1700
Data Index: 3071534 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9200. Min Range: -3.9200
Max Act: 3.7636. Min Act: -0.1700
Data Index: 1839213 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9200. Min Range: -3.9200
Max Act: 3.7323. Min Act: -0.1700
Data Index: 1646646 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9200. Min Range: -3.9200
Max Act: 3.7323. Min Act: -0.1700
Data Index: 4236707 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9200. Min Range: -3.9200
Max Act: 3.7011. Min Act: -0.1700
Data Index: 1901485 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9200. Min Range: -3.9200
Max Act: 3.7011. Min Act: -0.1700
Data Index: 6206885 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9200. Min Range: -3.9200
Max Act: 3.6698. Min Act: -0.1700
Data Index: 7233087 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9200. Min Range: -3.9200
Max Act: 3.6698. Min Act: -0.1700
Data Index: 2694067 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9200. Min Range: -3.9200
Max Act: 3.6698. Min Act: -0.1700
Data Index: 2061165 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9200. Min Range: -3.9200
Max Act: 3.6698. Min Act: -0.1700
Data Index: 3020416 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #19