Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3484 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7996. Min Range: -7.7996
Max Act: 7.7996. Min Act: -0.1700
Data Index: 5475540 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7996. Min Range: -7.7996
Max Act: 7.6746. Min Act: -0.1700
Data Index: 5804861 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7996. Min Range: -7.7996
Max Act: 7.5808. Min Act: -0.1700
Data Index: 2575104 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7996. Min Range: -7.7996
Max Act: 7.6433. Min Act: -0.1700
Data Index: 1573461 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7996. Min Range: -7.7996
Max Act: 7.5496. Min Act: -0.1700
Data Index: 5535369 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7996. Min Range: -7.7996
Max Act: 7.5496. Min Act: -0.1700
Data Index: 2407790 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7996. Min Range: -7.7996
Max Act: 7.5496. Min Act: -0.1700
Data Index: 7249403 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7996. Min Range: -7.7996
Max Act: 7.5496. Min Act: -0.1700
Data Index: 428077 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7996. Min Range: -7.7996
Max Act: 7.5496. Min Act: -0.1700
Data Index: 6208825 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7996. Min Range: -7.7996
Max Act: 7.5183. Min Act: -0.1700
Data Index: 3573317 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7996. Min Range: -7.7996
Max Act: 7.5183. Min Act: -0.1700
Data Index: 3734820 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7996. Min Range: -7.7996
Max Act: 7.5183. Min Act: -0.1700
Data Index: 7232954 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7996. Min Range: -7.7996
Max Act: 7.4871. Min Act: -0.1700
Data Index: 2013553 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7996. Min Range: -7.7996
Max Act: 7.4871. Min Act: -0.1700
Data Index: 6208826 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7996. Min Range: -7.7996
Max Act: 7.4558. Min Act: -0.1700
Data Index: 5792959 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7996. Min Range: -7.7996
Max Act: 7.4871. Min Act: -0.1700
Data Index: 908842 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7996. Min Range: -7.7996
Max Act: 7.4871. Min Act: -0.1700
Data Index: 6850766 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7996. Min Range: -7.7996
Max Act: 7.4558. Min Act: -0.1700
Data Index: 2407789 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7996. Min Range: -7.7996
Max Act: 7.4246. Min Act: -0.1700
Data Index: 3371938 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7996. Min Range: -7.7996
Max Act: 7.4558. Min Act: -0.1700
Data Index: 5737188 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #19