Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2722 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6275. Min Range: -4.6275
Max Act: 4.6275. Min Act: -0.1700
Data Index: 6106724 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6275. Min Range: -4.6275
Max Act: 4.4400. Min Act: -0.1700
Data Index: 2384255 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6275. Min Range: -4.6275
Max Act: 4.4712. Min Act: -0.1700
Data Index: 3392201 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6275. Min Range: -4.6275
Max Act: 4.4712. Min Act: -0.1700
Data Index: 3324346 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6275. Min Range: -4.6275
Max Act: 4.4712. Min Act: -0.1700
Data Index: 4882678 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6275. Min Range: -4.6275
Max Act: 4.4400. Min Act: -0.1700
Data Index: 7380227 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6275. Min Range: -4.6275
Max Act: 4.4400. Min Act: -0.1700
Data Index: 4159318 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6275. Min Range: -4.6275
Max Act: 4.4400. Min Act: -0.1700
Data Index: 7393055 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6275. Min Range: -4.6275
Max Act: 4.4400. Min Act: -0.1700
Data Index: 4882680 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6275. Min Range: -4.6275
Max Act: 4.4400. Min Act: -0.1700
Data Index: 5975052 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6275. Min Range: -4.6275
Max Act: 4.4400. Min Act: -0.1700
Data Index: 4000711 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6275. Min Range: -4.6275
Max Act: 4.4087. Min Act: -0.1700
Data Index: 2867083 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6275. Min Range: -4.6275
Max Act: 4.4087. Min Act: -0.1700
Data Index: 838487 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6275. Min Range: -4.6275
Max Act: 4.3775. Min Act: -0.1700
Data Index: 6870910 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6275. Min Range: -4.6275
Max Act: 4.3775. Min Act: -0.1700
Data Index: 3291742 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6275. Min Range: -4.6275
Max Act: 4.3775. Min Act: -0.1700
Data Index: 1760823 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6275. Min Range: -4.6275
Max Act: 4.3462. Min Act: -0.1700
Data Index: 6760074 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6275. Min Range: -4.6275
Max Act: 4.3775. Min Act: -0.1700
Data Index: 5618792 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6275. Min Range: -4.6275
Max Act: 4.3775. Min Act: -0.1700
Data Index: 3964498 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6275. Min Range: -4.6275
Max Act: 4.3775. Min Act: -0.1700
Data Index: 3671695 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #19