Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2282 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.2852. Min Range: -7.2852
Max Act: 7.2852. Min Act: -0.1700
Data Index: 1572578 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2852. Min Range: -7.2852
Max Act: 7.2852. Min Act: -0.1700
Data Index: 366599 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2852. Min Range: -7.2852
Max Act: 7.2539. Min Act: -0.1700
Data Index: 6333934 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2852. Min Range: -7.2852
Max Act: 7.1602. Min Act: -0.1700
Data Index: 3947027 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2852. Min Range: -7.2852
Max Act: 7.0664. Min Act: -0.1700
Data Index: 4883911 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2852. Min Range: -7.2852
Max Act: 7.0664. Min Act: -0.1700
Data Index: 7704541 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2852. Min Range: -7.2852
Max Act: 7.0664. Min Act: -0.1700
Data Index: 1937516 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2852. Min Range: -7.2852
Max Act: 7.0664. Min Act: -0.1700
Data Index: 5804389 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2852. Min Range: -7.2852
Max Act: 7.0039. Min Act: -0.1700
Data Index: 4816250 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2852. Min Range: -7.2852
Max Act: 7.0039. Min Act: -0.1700
Data Index: 2201801 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2852. Min Range: -7.2852
Max Act: 6.9727. Min Act: -0.1700
Data Index: 6008366 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2852. Min Range: -7.2852
Max Act: 6.9414. Min Act: -0.1700
Data Index: 6145521 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2852. Min Range: -7.2852
Max Act: 6.9414. Min Act: -0.1700
Data Index: 2594347 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2852. Min Range: -7.2852
Max Act: 6.9102. Min Act: -0.1700
Data Index: 8000705 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2852. Min Range: -7.2852
Max Act: 6.9102. Min Act: -0.1700
Data Index: 8117636 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2852. Min Range: -7.2852
Max Act: 6.8477. Min Act: -0.1700
Data Index: 6728294 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2852. Min Range: -7.2852
Max Act: 6.8789. Min Act: -0.1700
Data Index: 5770076 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2852. Min Range: -7.2852
Max Act: 6.8477. Min Act: -0.1700
Data Index: 310113 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2852. Min Range: -7.2852
Max Act: 6.7852. Min Act: -0.1700
Data Index: 1256313 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2852. Min Range: -7.2852
Max Act: 6.7852. Min Act: -0.1700
Data Index: 3940741 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #19