Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5183 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.9719. Min Range: -8.9719
Max Act: 8.9719. Min Act: -0.1700
Data Index: 7252869 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.9719. Min Range: -8.9719
Max Act: 8.1594. Min Act: -0.1700
Data Index: 5680982 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.9719. Min Range: -8.9719
Max Act: 8.0969. Min Act: -0.1700
Data Index: 6940906 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.9719. Min Range: -8.9719
Max Act: 8.0656. Min Act: -0.1700
Data Index: 7451604 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.9719. Min Range: -8.9719
Max Act: 8.0344. Min Act: -0.1700
Data Index: 2882925 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.9719. Min Range: -8.9719
Max Act: 8.0344. Min Act: -0.1700
Data Index: 7719876 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.9719. Min Range: -8.9719
Max Act: 7.9094. Min Act: -0.1700
Data Index: 376714 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.9719. Min Range: -8.9719
Max Act: 7.7844. Min Act: -0.1700
Data Index: 5657006 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.9719. Min Range: -8.9719
Max Act: 7.7531. Min Act: -0.1700
Data Index: 3572317 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.9719. Min Range: -8.9719
Max Act: 7.6906. Min Act: -0.1700
Data Index: 5892224 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.9719. Min Range: -8.9719
Max Act: 7.6906. Min Act: -0.1700
Data Index: 8368040 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.9719. Min Range: -8.9719
Max Act: 7.6906. Min Act: -0.1700
Data Index: 831927 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.9719. Min Range: -8.9719
Max Act: 7.6906. Min Act: -0.1700
Data Index: 6506312 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.9719. Min Range: -8.9719
Max Act: 7.6906. Min Act: -0.1700
Data Index: 1905365 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.9719. Min Range: -8.9719
Max Act: 7.6906. Min Act: -0.1700
Data Index: 785821 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.9719. Min Range: -8.9719
Max Act: 7.6281. Min Act: -0.1700
Data Index: 2510789 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.9719. Min Range: -8.9719
Max Act: 7.6594. Min Act: -0.1700
Data Index: 4767545 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.9719. Min Range: -8.9719
Max Act: 7.5969. Min Act: -0.1700
Data Index: 3406739 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.9719. Min Range: -8.9719
Max Act: 7.5969. Min Act: -0.1700
Data Index: 2695225 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.9719. Min Range: -8.9719
Max Act: 7.5969. Min Act: -0.1700
Data Index: 105330 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #19