Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2717 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.1768. Min Range: -4.1768
Max Act: 4.1768. Min Act: -0.1700
Data Index: 969596 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1768. Min Range: -4.1768
Max Act: 4.1455. Min Act: -0.1700
Data Index: 3273795 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1768. Min Range: -4.1768
Max Act: 4.0830. Min Act: -0.1700
Data Index: 7633911 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1768. Min Range: -4.1768
Max Act: 4.0205. Min Act: -0.1700
Data Index: 4735686 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1768. Min Range: -4.1768
Max Act: 3.9892. Min Act: -0.1700
Data Index: 2078933 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1768. Min Range: -4.1768
Max Act: 3.9892. Min Act: -0.1700
Data Index: 7330497 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1768. Min Range: -4.1768
Max Act: 3.9892. Min Act: -0.1700
Data Index: 7897174 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1768. Min Range: -4.1768
Max Act: 3.9580. Min Act: -0.1700
Data Index: 5030948 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1768. Min Range: -4.1768
Max Act: 3.9267. Min Act: -0.1700
Data Index: 5033509 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1768. Min Range: -4.1768
Max Act: 3.9267. Min Act: -0.1700
Data Index: 6733250 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1768. Min Range: -4.1768
Max Act: 3.8955. Min Act: -0.1700
Data Index: 4705962 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1768. Min Range: -4.1768
Max Act: 3.8955. Min Act: -0.1700
Data Index: 437683 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1768. Min Range: -4.1768
Max Act: 3.8955. Min Act: -0.1700
Data Index: 7955340 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1768. Min Range: -4.1768
Max Act: 3.8955. Min Act: -0.1700
Data Index: 6429323 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1768. Min Range: -4.1768
Max Act: 3.8642. Min Act: -0.1700
Data Index: 7517442 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1768. Min Range: -4.1768
Max Act: 3.8329. Min Act: -0.1700
Data Index: 5655789 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1768. Min Range: -4.1768
Max Act: 3.8642. Min Act: -0.1700
Data Index: 6104592 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1768. Min Range: -4.1768
Max Act: 3.8642. Min Act: -0.1700
Data Index: 6496762 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1768. Min Range: -4.1768
Max Act: 3.8642. Min Act: -0.1700
Data Index: 4478404 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1768. Min Range: -4.1768
Max Act: 3.8642. Min Act: -0.1700
Data Index: 4483715 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #19