Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5392 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4516. Min Range: -5.4516
Max Act: 5.4516. Min Act: -0.1700
Data Index: 1756919 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4516. Min Range: -5.4516
Max Act: 5.3266. Min Act: -0.1700
Data Index: 4033376 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4516. Min Range: -5.4516
Max Act: 5.2016. Min Act: -0.1700
Data Index: 2676900 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4516. Min Range: -5.4516
Max Act: 5.1703. Min Act: -0.1700
Data Index: 7445992 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4516. Min Range: -5.4516
Max Act: 5.1078. Min Act: -0.1700
Data Index: 3949083 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4516. Min Range: -5.4516
Max Act: 5.1078. Min Act: -0.1700
Data Index: 6877719 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4516. Min Range: -5.4516
Max Act: 5.0766. Min Act: -0.1700
Data Index: 5683329 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4516. Min Range: -5.4516
Max Act: 5.0453. Min Act: -0.1700
Data Index: 2140624 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4516. Min Range: -5.4516
Max Act: 5.0453. Min Act: -0.1700
Data Index: 3757893 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4516. Min Range: -5.4516
Max Act: 4.9828. Min Act: -0.1700
Data Index: 5767454 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4516. Min Range: -5.4516
Max Act: 4.9516. Min Act: -0.1700
Data Index: 4125525 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4516. Min Range: -5.4516
Max Act: 4.9516. Min Act: -0.1700
Data Index: 5878463 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4516. Min Range: -5.4516
Max Act: 4.9828. Min Act: -0.1700
Data Index: 1750674 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4516. Min Range: -5.4516
Max Act: 4.9516. Min Act: -0.1700
Data Index: 945238 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4516. Min Range: -5.4516
Max Act: 4.9516. Min Act: -0.1700
Data Index: 6904788 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4516. Min Range: -5.4516
Max Act: 4.9516. Min Act: -0.1700
Data Index: 3509327 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4516. Min Range: -5.4516
Max Act: 4.9203. Min Act: -0.1700
Data Index: 5373009 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4516. Min Range: -5.4516
Max Act: 4.9203. Min Act: -0.1700
Data Index: 8482794 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4516. Min Range: -5.4516
Max Act: 4.8891. Min Act: -0.1700
Data Index: 6786513 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4516. Min Range: -5.4516
Max Act: 4.8891. Min Act: -0.1700
Data Index: 497238 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #19