Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2110 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.1394. Min Range: -3.1394
Max Act: 3.1394. Min Act: -0.1700
Data Index: 6997808 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1394. Min Range: -3.1394
Max Act: 3.0132. Min Act: -0.1700
Data Index: 577878 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1394. Min Range: -3.1394
Max Act: 2.9658. Min Act: -0.1700
Data Index: 5986319 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1394. Min Range: -3.1394
Max Act: 2.8707. Min Act: -0.1700
Data Index: 2727815 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1394. Min Range: -3.1394
Max Act: 2.8548. Min Act: -0.1700
Data Index: 7396486 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1394. Min Range: -3.1394
Max Act: 2.8389. Min Act: -0.1700
Data Index: 3029807 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1394. Min Range: -3.1394
Max Act: 2.8389. Min Act: -0.1700
Data Index: 7254905 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1394. Min Range: -3.1394
Max Act: 2.8389. Min Act: -0.1700
Data Index: 577886 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1394. Min Range: -3.1394
Max Act: 2.8548. Min Act: -0.1700
Data Index: 2252923 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1394. Min Range: -3.1394
Max Act: 2.8230. Min Act: -0.1700
Data Index: 577871 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1394. Min Range: -3.1394
Max Act: 2.8230. Min Act: -0.1700
Data Index: 3094704 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1394. Min Range: -3.1394
Max Act: 2.8071. Min Act: -0.1700
Data Index: 2094865 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1394. Min Range: -3.1394
Max Act: 2.8071. Min Act: -0.1700
Data Index: 2892779 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1394. Min Range: -3.1394
Max Act: 2.8071. Min Act: -0.1700
Data Index: 3720321 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1394. Min Range: -3.1394
Max Act: 2.8071. Min Act: -0.1700
Data Index: 7517248 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1394. Min Range: -3.1394
Max Act: 2.8230. Min Act: -0.1700
Data Index: 577861 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1394. Min Range: -3.1394
Max Act: 2.7753. Min Act: -0.1700
Data Index: 1877983 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1394. Min Range: -3.1394
Max Act: 2.7912. Min Act: -0.1700
Data Index: 432226 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1394. Min Range: -3.1394
Max Act: 2.8071. Min Act: -0.1700
Data Index: 3400908 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1394. Min Range: -3.1394
Max Act: 2.7753. Min Act: -0.1700
Data Index: 1455761 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #19