Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4295 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.0097. Min Range: -9.0097
Max Act: 9.0097. Min Act: -0.1700
Data Index: 6274423 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.0097. Min Range: -9.0097
Max Act: 8.9472. Min Act: -0.1700
Data Index: 4825481 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.0097. Min Range: -9.0097
Max Act: 8.8847. Min Act: -0.1700
Data Index: 8113540 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.0097. Min Range: -9.0097
Max Act: 8.8847. Min Act: -0.1700
Data Index: 2294066 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.0097. Min Range: -9.0097
Max Act: 8.8847. Min Act: -0.1700
Data Index: 7584808 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.0097. Min Range: -9.0097
Max Act: 8.8847. Min Act: -0.1700
Data Index: 7105336 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.0097. Min Range: -9.0097
Max Act: 8.8847. Min Act: -0.1700
Data Index: 6493001 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.0097. Min Range: -9.0097
Max Act: 8.8847. Min Act: -0.1700
Data Index: 1838255 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.0097. Min Range: -9.0097
Max Act: 8.9472. Min Act: -0.1700
Data Index: 6350371 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.0097. Min Range: -9.0097
Max Act: 8.8847. Min Act: -0.1700
Data Index: 6018705 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.0097. Min Range: -9.0097
Max Act: 8.8847. Min Act: -0.1700
Data Index: 5318977 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.0097. Min Range: -9.0097
Max Act: 8.8847. Min Act: -0.1700
Data Index: 216947 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.0097. Min Range: -9.0097
Max Act: 8.8847. Min Act: -0.1700
Data Index: 4757534 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.0097. Min Range: -9.0097
Max Act: 8.8847. Min Act: -0.1700
Data Index: 4432711 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.0097. Min Range: -9.0097
Max Act: 8.8847. Min Act: -0.1700
Data Index: 4207957 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.0097. Min Range: -9.0097
Max Act: 8.8847. Min Act: -0.1700
Data Index: 3696545 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.0097. Min Range: -9.0097
Max Act: 8.8847. Min Act: -0.1700
Data Index: 3628870 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.0097. Min Range: -9.0097
Max Act: 8.8847. Min Act: -0.1700
Data Index: 3353280 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.0097. Min Range: -9.0097
Max Act: 8.8847. Min Act: -0.1700
Data Index: 2859466 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.0097. Min Range: -9.0097
Max Act: 8.8847. Min Act: -0.1700
Data Index: 2852576 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #19