Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2961 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3245. Min Range: -6.3245
Max Act: 6.3245. Min Act: -0.1700
Data Index: 7436227 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3245. Min Range: -6.3245
Max Act: 6.2308. Min Act: -0.1700
Data Index: 4291825 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3245. Min Range: -6.3245
Max Act: 6.1370. Min Act: -0.1700
Data Index: 6228242 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3245. Min Range: -6.3245
Max Act: 6.1683. Min Act: -0.1700
Data Index: 1649873 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3245. Min Range: -6.3245
Max Act: 6.1058. Min Act: -0.1700
Data Index: 6020526 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3245. Min Range: -6.3245
Max Act: 6.0745. Min Act: -0.1700
Data Index: 1423822 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3245. Min Range: -6.3245
Max Act: 6.0745. Min Act: -0.1700
Data Index: 6491767 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3245. Min Range: -6.3245
Max Act: 6.0433. Min Act: -0.1700
Data Index: 6491766 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3245. Min Range: -6.3245
Max Act: 6.0433. Min Act: -0.1700
Data Index: 160385 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3245. Min Range: -6.3245
Max Act: 6.0433. Min Act: -0.1700
Data Index: 1423823 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3245. Min Range: -6.3245
Max Act: 6.0120. Min Act: -0.1700
Data Index: 8714456 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3245. Min Range: -6.3245
Max Act: 6.0433. Min Act: -0.1700
Data Index: 4791239 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3245. Min Range: -6.3245
Max Act: 6.0120. Min Act: -0.1700
Data Index: 1423825 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3245. Min Range: -6.3245
Max Act: 5.9808. Min Act: -0.1700
Data Index: 3282899 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3245. Min Range: -6.3245
Max Act: 5.9495. Min Act: -0.1700
Data Index: 4164729 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3245. Min Range: -6.3245
Max Act: 5.9808. Min Act: -0.1700
Data Index: 8164039 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3245. Min Range: -6.3245
Max Act: 5.9495. Min Act: -0.1700
Data Index: 8224038 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3245. Min Range: -6.3245
Max Act: 5.9183. Min Act: -0.1700
Data Index: 1728298 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3245. Min Range: -6.3245
Max Act: 5.9183. Min Act: -0.1700
Data Index: 406700 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3245. Min Range: -6.3245
Max Act: 5.9183. Min Act: -0.1700
Data Index: 5843386 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #19