Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3882 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2379. Min Range: -6.2379
Max Act: 6.2379. Min Act: -0.1700
Data Index: 6938767 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2379. Min Range: -6.2379
Max Act: 6.2067. Min Act: -0.1700
Data Index: 71522 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2379. Min Range: -6.2379
Max Act: 6.1754. Min Act: -0.1700
Data Index: 4113609 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2379. Min Range: -6.2379
Max Act: 6.1754. Min Act: -0.1700
Data Index: 2138129 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2379. Min Range: -6.2379
Max Act: 6.1442. Min Act: -0.1700
Data Index: 1792893 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2379. Min Range: -6.2379
Max Act: 6.1442. Min Act: -0.1700
Data Index: 3275249 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2379. Min Range: -6.2379
Max Act: 6.1129. Min Act: -0.1700
Data Index: 1150709 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2379. Min Range: -6.2379
Max Act: 6.0817. Min Act: -0.1700
Data Index: 2502993 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2379. Min Range: -6.2379
Max Act: 6.0504. Min Act: -0.1700
Data Index: 875998 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2379. Min Range: -6.2379
Max Act: 6.0504. Min Act: -0.1700
Data Index: 7766247 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2379. Min Range: -6.2379
Max Act: 6.0192. Min Act: -0.1700
Data Index: 3302623 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2379. Min Range: -6.2379
Max Act: 6.0192. Min Act: -0.1700
Data Index: 8515504 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2379. Min Range: -6.2379
Max Act: 5.9879. Min Act: -0.1700
Data Index: 5576736 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2379. Min Range: -6.2379
Max Act: 5.9879. Min Act: -0.1700
Data Index: 1511948 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2379. Min Range: -6.2379
Max Act: 6.0192. Min Act: -0.1700
Data Index: 5379226 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2379. Min Range: -6.2379
Max Act: 5.9254. Min Act: -0.1700
Data Index: 4429545 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2379. Min Range: -6.2379
Max Act: 5.9567. Min Act: -0.1700
Data Index: 3653995 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2379. Min Range: -6.2379
Max Act: 5.9567. Min Act: -0.1700
Data Index: 2519183 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2379. Min Range: -6.2379
Max Act: 5.9254. Min Act: -0.1700
Data Index: 4678895 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2379. Min Range: -6.2379
Max Act: 5.9254. Min Act: -0.1700
Data Index: 4187418 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #19