Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2456 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.5501. Min Range: -5.5501
Max Act: 5.5501. Min Act: -0.1700
Data Index: 622914 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5501. Min Range: -5.5501
Max Act: 5.4876. Min Act: -0.1700
Data Index: 7261280 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5501. Min Range: -5.5501
Max Act: 5.3001. Min Act: -0.1700
Data Index: 3701747 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5501. Min Range: -5.5501
Max Act: 5.2688. Min Act: -0.1700
Data Index: 321330 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5501. Min Range: -5.5501
Max Act: 5.2376. Min Act: -0.1700
Data Index: 888262 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5501. Min Range: -5.5501
Max Act: 5.1751. Min Act: -0.1700
Data Index: 6579579 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5501. Min Range: -5.5501
Max Act: 5.1126. Min Act: -0.1700
Data Index: 5054100 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5501. Min Range: -5.5501
Max Act: 5.1438. Min Act: -0.1700
Data Index: 2416667 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5501. Min Range: -5.5501
Max Act: 5.1438. Min Act: -0.1700
Data Index: 888263 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5501. Min Range: -5.5501
Max Act: 5.0813. Min Act: -0.1700
Data Index: 146951 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5501. Min Range: -5.5501
Max Act: 5.0813. Min Act: -0.1700
Data Index: 5304190 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5501. Min Range: -5.5501
Max Act: 5.0813. Min Act: -0.1700
Data Index: 7645349 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5501. Min Range: -5.5501
Max Act: 5.0813. Min Act: -0.1700
Data Index: 3919293 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5501. Min Range: -5.5501
Max Act: 5.0813. Min Act: -0.1700
Data Index: 7804986 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5501. Min Range: -5.5501
Max Act: 5.0813. Min Act: -0.1700
Data Index: 1424227 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5501. Min Range: -5.5501
Max Act: 5.0501. Min Act: -0.1700
Data Index: 8543127 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5501. Min Range: -5.5501
Max Act: 5.0501. Min Act: -0.1700
Data Index: 3248368 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5501. Min Range: -5.5501
Max Act: 5.0501. Min Act: -0.1700
Data Index: 3800545 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5501. Min Range: -5.5501
Max Act: 5.0501. Min Act: -0.1700
Data Index: 7363619 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5501. Min Range: -5.5501
Max Act: 5.0501. Min Act: -0.1700
Data Index: 4913804 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #19