Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2429 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.2251. Min Range: -4.2251
Max Act: 4.2251. Min Act: -0.1700
Data Index: 5110113 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2251. Min Range: -4.2251
Max Act: 4.1939. Min Act: -0.1700
Data Index: 5811588 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2251. Min Range: -4.2251
Max Act: 4.1939. Min Act: -0.1700
Data Index: 2100767 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2251. Min Range: -4.2251
Max Act: 4.1001. Min Act: -0.1700
Data Index: 4176828 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2251. Min Range: -4.2251
Max Act: 4.1001. Min Act: -0.1700
Data Index: 5339947 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2251. Min Range: -4.2251
Max Act: 4.1001. Min Act: -0.1700
Data Index: 4772057 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2251. Min Range: -4.2251
Max Act: 4.0688. Min Act: -0.1700
Data Index: 3777648 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2251. Min Range: -4.2251
Max Act: 4.0688. Min Act: -0.1700
Data Index: 7019714 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2251. Min Range: -4.2251
Max Act: 4.0688. Min Act: -0.1700
Data Index: 694029 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2251. Min Range: -4.2251
Max Act: 4.0376. Min Act: -0.1700
Data Index: 2761985 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2251. Min Range: -4.2251
Max Act: 4.0376. Min Act: -0.1700
Data Index: 7420425 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2251. Min Range: -4.2251
Max Act: 4.0376. Min Act: -0.1700
Data Index: 4415294 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2251. Min Range: -4.2251
Max Act: 4.0376. Min Act: -0.1700
Data Index: 5429307 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2251. Min Range: -4.2251
Max Act: 4.0063. Min Act: -0.1700
Data Index: 1063664 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2251. Min Range: -4.2251
Max Act: 3.9438. Min Act: -0.1700
Data Index: 2662424 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2251. Min Range: -4.2251
Max Act: 3.9751. Min Act: -0.1700
Data Index: 3785961 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2251. Min Range: -4.2251
Max Act: 3.9751. Min Act: -0.1700
Data Index: 8604929 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2251. Min Range: -4.2251
Max Act: 3.9751. Min Act: -0.1700
Data Index: 4713741 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2251. Min Range: -4.2251
Max Act: 3.9751. Min Act: -0.1700
Data Index: 5927323 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2251. Min Range: -4.2251
Max Act: 3.9438. Min Act: -0.1700
Data Index: 5556928 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #19