Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4073 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.0357. Min Range: -8.0357
Max Act: 8.0357. Min Act: -0.1700
Data Index: 6932659 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0357. Min Range: -8.0357
Max Act: 7.7857. Min Act: -0.1700
Data Index: 1013066 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0357. Min Range: -8.0357
Max Act: 7.7232. Min Act: -0.1700
Data Index: 1579955 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0357. Min Range: -8.0357
Max Act: 7.6295. Min Act: -0.1700
Data Index: 2630378 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0357. Min Range: -8.0357
Max Act: 7.5357. Min Act: -0.1700
Data Index: 3387934 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0357. Min Range: -8.0357
Max Act: 7.5357. Min Act: -0.1700
Data Index: 7819009 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0357. Min Range: -8.0357
Max Act: 7.4420. Min Act: -0.1700
Data Index: 5942766 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0357. Min Range: -8.0357
Max Act: 7.4732. Min Act: -0.1700
Data Index: 4593496 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0357. Min Range: -8.0357
Max Act: 7.5357. Min Act: -0.1700
Data Index: 941046 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0357. Min Range: -8.0357
Max Act: 7.4107. Min Act: -0.1700
Data Index: 133698 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0357. Min Range: -8.0357
Max Act: 7.3170. Min Act: -0.1700
Data Index: 4144230 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0357. Min Range: -8.0357
Max Act: 7.3482. Min Act: -0.1700
Data Index: 3387005 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0357. Min Range: -8.0357
Max Act: 7.3795. Min Act: -0.1700
Data Index: 3584241 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0357. Min Range: -8.0357
Max Act: 7.3482. Min Act: -0.1700
Data Index: 3855653 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0357. Min Range: -8.0357
Max Act: 7.3170. Min Act: -0.1700
Data Index: 5446508 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0357. Min Range: -8.0357
Max Act: 7.2857. Min Act: -0.1700
Data Index: 7651965 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0357. Min Range: -8.0357
Max Act: 7.3170. Min Act: -0.1700
Data Index: 6384219 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0357. Min Range: -8.0357
Max Act: 7.3170. Min Act: -0.1700
Data Index: 5538618 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0357. Min Range: -8.0357
Max Act: 7.2857. Min Act: -0.1700
Data Index: 3293863 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0357. Min Range: -8.0357
Max Act: 7.2232. Min Act: -0.1700
Data Index: 7662892 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #19