Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3863 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.0176. Min Range: -9.0176
Max Act: 9.0176. Min Act: -0.1700
Data Index: 3096655 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.0176. Min Range: -9.0176
Max Act: 8.9551. Min Act: -0.1700
Data Index: 5003492 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.0176. Min Range: -9.0176
Max Act: 8.8301. Min Act: -0.1700
Data Index: 8241010 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.0176. Min Range: -9.0176
Max Act: 8.7676. Min Act: -0.1700
Data Index: 7776251 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.0176. Min Range: -9.0176
Max Act: 8.6426. Min Act: -0.1700
Data Index: 680749 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.0176. Min Range: -9.0176
Max Act: 8.5801. Min Act: -0.1700
Data Index: 353170 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.0176. Min Range: -9.0176
Max Act: 8.3926. Min Act: -0.1700
Data Index: 421768 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.0176. Min Range: -9.0176
Max Act: 8.3926. Min Act: -0.1700
Data Index: 6062666 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.0176. Min Range: -9.0176
Max Act: 8.2676. Min Act: -0.1700
Data Index: 945468 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.0176. Min Range: -9.0176
Max Act: 8.2676. Min Act: -0.1700
Data Index: 4083481 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.0176. Min Range: -9.0176
Max Act: 8.1426. Min Act: -0.1700
Data Index: 1783597 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.0176. Min Range: -9.0176
Max Act: 8.2051. Min Act: -0.1700
Data Index: 7769537 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.0176. Min Range: -9.0176
Max Act: 8.2051. Min Act: -0.1700
Data Index: 5394554 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.0176. Min Range: -9.0176
Max Act: 8.0801. Min Act: -0.1700
Data Index: 271921 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.0176. Min Range: -9.0176
Max Act: 8.1426. Min Act: -0.1700
Data Index: 8649034 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.0176. Min Range: -9.0176
Max Act: 8.1426. Min Act: -0.1700
Data Index: 7550455 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.0176. Min Range: -9.0176
Max Act: 8.1426. Min Act: -0.1700
Data Index: 4327632 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.0176. Min Range: -9.0176
Max Act: 8.1426. Min Act: -0.1700
Data Index: 3540419 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.0176. Min Range: -9.0176
Max Act: 8.1426. Min Act: -0.1700
Data Index: 734336 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.0176. Min Range: -9.0176
Max Act: 8.1426. Min Act: -0.1700
Data Index: 2721173 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #19