Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 769 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.7578. Min Range: -4.7578
Max Act: 4.7578. Min Act: -0.1700
Data Index: 8214165 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7578. Min Range: -4.7578
Max Act: 4.6016. Min Act: -0.1700
Data Index: 3765992 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7578. Min Range: -4.7578
Max Act: 4.5391. Min Act: -0.1700
Data Index: 4921492 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7578. Min Range: -4.7578
Max Act: 4.5391. Min Act: -0.1700
Data Index: 5215285 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7578. Min Range: -4.7578
Max Act: 4.5078. Min Act: -0.1700
Data Index: 8579290 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7578. Min Range: -4.7578
Max Act: 4.5391. Min Act: -0.1700
Data Index: 3885907 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7578. Min Range: -4.7578
Max Act: 4.4453. Min Act: -0.1700
Data Index: 4139382 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7578. Min Range: -4.7578
Max Act: 4.4453. Min Act: -0.1700
Data Index: 6362106 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7578. Min Range: -4.7578
Max Act: 4.4141. Min Act: -0.1700
Data Index: 2813002 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7578. Min Range: -4.7578
Max Act: 4.4141. Min Act: -0.1700
Data Index: 6842687 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7578. Min Range: -4.7578
Max Act: 4.4141. Min Act: -0.1700
Data Index: 3716983 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7578. Min Range: -4.7578
Max Act: 4.4141. Min Act: -0.1700
Data Index: 5628145 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7578. Min Range: -4.7578
Max Act: 4.3828. Min Act: -0.1700
Data Index: 4813913 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7578. Min Range: -4.7578
Max Act: 4.3516. Min Act: -0.1700
Data Index: 3286188 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7578. Min Range: -4.7578
Max Act: 4.3203. Min Act: -0.1700
Data Index: 1564187 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7578. Min Range: -4.7578
Max Act: 4.3203. Min Act: -0.1700
Data Index: 8154833 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7578. Min Range: -4.7578
Max Act: 4.2891. Min Act: -0.1700
Data Index: 3039561 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7578. Min Range: -4.7578
Max Act: 4.2578. Min Act: -0.1700
Data Index: 5882276 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7578. Min Range: -4.7578
Max Act: 4.2891. Min Act: -0.1700
Data Index: 1007681 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7578. Min Range: -4.7578
Max Act: 4.2578. Min Act: -0.1700
Data Index: 7570593 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #19