Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5736 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.5147. Min Range: -8.5147
Max Act: 8.5147. Min Act: -0.1700
Data Index: 4273214 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5147. Min Range: -8.5147
Max Act: 6.7960. Min Act: -0.1700
Data Index: 3610367 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5147. Min Range: -8.5147
Max Act: 6.7960. Min Act: -0.1700
Data Index: 4311769 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5147. Min Range: -8.5147
Max Act: 6.7960. Min Act: -0.1700
Data Index: 2315879 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5147. Min Range: -8.5147
Max Act: 6.7022. Min Act: -0.1700
Data Index: 6313405 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5147. Min Range: -8.5147
Max Act: 6.6710. Min Act: -0.1700
Data Index: 552373 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5147. Min Range: -8.5147
Max Act: 6.7022. Min Act: -0.1700
Data Index: 4761410 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5147. Min Range: -8.5147
Max Act: 6.6397. Min Act: -0.1700
Data Index: 8007239 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5147. Min Range: -8.5147
Max Act: 6.6085. Min Act: -0.1700
Data Index: 7443829 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5147. Min Range: -8.5147
Max Act: 6.6085. Min Act: -0.1700
Data Index: 212267 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5147. Min Range: -8.5147
Max Act: 6.6085. Min Act: -0.1700
Data Index: 1725274 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5147. Min Range: -8.5147
Max Act: 6.5460. Min Act: -0.1700
Data Index: 4253424 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5147. Min Range: -8.5147
Max Act: 6.5460. Min Act: -0.1700
Data Index: 6433994 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5147. Min Range: -8.5147
Max Act: 6.5772. Min Act: -0.1700
Data Index: 8483364 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5147. Min Range: -8.5147
Max Act: 6.5147. Min Act: -0.1700
Data Index: 251626 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5147. Min Range: -8.5147
Max Act: 6.5147. Min Act: -0.1700
Data Index: 8574418 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5147. Min Range: -8.5147
Max Act: 6.5147. Min Act: -0.1700
Data Index: 5064674 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5147. Min Range: -8.5147
Max Act: 6.5460. Min Act: -0.1700
Data Index: 2771408 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5147. Min Range: -8.5147
Max Act: 6.4835. Min Act: -0.1700
Data Index: 5432296 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5147. Min Range: -8.5147
Max Act: 6.4835. Min Act: -0.1700
Data Index: 7443831 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #19