Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 313 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2745. Min Range: -8.2745
Max Act: 8.2745. Min Act: -0.1700
Data Index: 4968250 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2745. Min Range: -8.2745
Max Act: 8.2120. Min Act: -0.1700
Data Index: 5339182 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2745. Min Range: -8.2745
Max Act: 8.1495. Min Act: -0.1700
Data Index: 1413825 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2745. Min Range: -8.2745
Max Act: 8.0245. Min Act: -0.1700
Data Index: 5792564 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2745. Min Range: -8.2745
Max Act: 7.9620. Min Act: -0.1700
Data Index: 7988051 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2745. Min Range: -8.2745
Max Act: 7.8995. Min Act: -0.1700
Data Index: 6563509 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2745. Min Range: -8.2745
Max Act: 7.9620. Min Act: -0.1700
Data Index: 7726197 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2745. Min Range: -8.2745
Max Act: 7.8995. Min Act: -0.1700
Data Index: 8700918 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2745. Min Range: -8.2745
Max Act: 7.8995. Min Act: -0.1700
Data Index: 4552313 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2745. Min Range: -8.2745
Max Act: 7.8995. Min Act: -0.1700
Data Index: 1787699 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2745. Min Range: -8.2745
Max Act: 7.7745. Min Act: -0.1700
Data Index: 3912397 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2745. Min Range: -8.2745
Max Act: 7.8370. Min Act: -0.1700
Data Index: 2042114 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2745. Min Range: -8.2745
Max Act: 7.8370. Min Act: -0.1700
Data Index: 3996740 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2745. Min Range: -8.2745
Max Act: 7.8370. Min Act: -0.1700
Data Index: 532674 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2745. Min Range: -8.2745
Max Act: 7.8370. Min Act: -0.1700
Data Index: 3807849 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2745. Min Range: -8.2745
Max Act: 7.7745. Min Act: -0.1700
Data Index: 8312114 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2745. Min Range: -8.2745
Max Act: 7.7745. Min Act: -0.1700
Data Index: 2512231 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2745. Min Range: -8.2745
Max Act: 7.7745. Min Act: -0.1700
Data Index: 720620 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2745. Min Range: -8.2745
Max Act: 7.7433. Min Act: -0.1700
Data Index: 3046670 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2745. Min Range: -8.2745
Max Act: 7.7433. Min Act: -0.1700
Data Index: 5025930 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #19