Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4442 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3512. Min Range: -6.3512
Max Act: 6.3512. Min Act: -0.1700
Data Index: 5564677 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3512. Min Range: -6.3512
Max Act: 6.2575. Min Act: -0.1700
Data Index: 8160008 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3512. Min Range: -6.3512
Max Act: 6.1012. Min Act: -0.1700
Data Index: 6792202 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3512. Min Range: -6.3512
Max Act: 6.0075. Min Act: -0.1700
Data Index: 3894044 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3512. Min Range: -6.3512
Max Act: 6.0075. Min Act: -0.1700
Data Index: 3593166 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3512. Min Range: -6.3512
Max Act: 5.9762. Min Act: -0.1700
Data Index: 3828352 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3512. Min Range: -6.3512
Max Act: 5.9762. Min Act: -0.1700
Data Index: 1393197 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3512. Min Range: -6.3512
Max Act: 5.8825. Min Act: -0.1700
Data Index: 7878197 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3512. Min Range: -6.3512
Max Act: 5.8825. Min Act: -0.1700
Data Index: 8286424 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3512. Min Range: -6.3512
Max Act: 5.8825. Min Act: -0.1700
Data Index: 3918759 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3512. Min Range: -6.3512
Max Act: 5.8825. Min Act: -0.1700
Data Index: 8620704 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3512. Min Range: -6.3512
Max Act: 5.8825. Min Act: -0.1700
Data Index: 4966705 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3512. Min Range: -6.3512
Max Act: 5.8825. Min Act: -0.1700
Data Index: 4926892 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3512. Min Range: -6.3512
Max Act: 5.8512. Min Act: -0.1700
Data Index: 5068206 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3512. Min Range: -6.3512
Max Act: 5.8200. Min Act: -0.1700
Data Index: 387946 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3512. Min Range: -6.3512
Max Act: 5.8200. Min Act: -0.1700
Data Index: 1420440 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3512. Min Range: -6.3512
Max Act: 5.8200. Min Act: -0.1700
Data Index: 3534506 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3512. Min Range: -6.3512
Max Act: 5.7575. Min Act: -0.1700
Data Index: 5139065 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3512. Min Range: -6.3512
Max Act: 5.7575. Min Act: -0.1700
Data Index: 4767248 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3512. Min Range: -6.3512
Max Act: 5.7262. Min Act: -0.1700
Data Index: 5039302 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #19