Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4410 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.1486. Min Range: -9.1486
Max Act: 9.1486. Min Act: -0.1700
Data Index: 5233526 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.1486. Min Range: -9.1486
Max Act: 9.0861. Min Act: -0.1700
Data Index: 3349167 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.1486. Min Range: -9.1486
Max Act: 9.0861. Min Act: -0.1700
Data Index: 4650944 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.1486. Min Range: -9.1486
Max Act: 8.9611. Min Act: -0.1700
Data Index: 397465 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.1486. Min Range: -9.1486
Max Act: 8.8361. Min Act: -0.1700
Data Index: 3733268 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.1486. Min Range: -9.1486
Max Act: 8.7736. Min Act: -0.1700
Data Index: 3376563 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.1486. Min Range: -9.1486
Max Act: 8.7736. Min Act: -0.1700
Data Index: 215132 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.1486. Min Range: -9.1486
Max Act: 8.7736. Min Act: -0.1700
Data Index: 5011462 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.1486. Min Range: -9.1486
Max Act: 8.7736. Min Act: -0.1700
Data Index: 8628125 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.1486. Min Range: -9.1486
Max Act: 8.7736. Min Act: -0.1700
Data Index: 8354326 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.1486. Min Range: -9.1486
Max Act: 8.7736. Min Act: -0.1700
Data Index: 5975571 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.1486. Min Range: -9.1486
Max Act: 8.7111. Min Act: -0.1700
Data Index: 3325718 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.1486. Min Range: -9.1486
Max Act: 8.7111. Min Act: -0.1700
Data Index: 8793350 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.1486. Min Range: -9.1486
Max Act: 8.7111. Min Act: -0.1700
Data Index: 734893 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.1486. Min Range: -9.1486
Max Act: 8.7111. Min Act: -0.1700
Data Index: 4687158 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.1486. Min Range: -9.1486
Max Act: 8.7111. Min Act: -0.1700
Data Index: 7805488 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.1486. Min Range: -9.1486
Max Act: 8.7111. Min Act: -0.1700
Data Index: 7286530 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.1486. Min Range: -9.1486
Max Act: 8.7111. Min Act: -0.1700
Data Index: 4290646 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.1486. Min Range: -9.1486
Max Act: 8.7111. Min Act: -0.1700
Data Index: 2340592 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.1486. Min Range: -9.1486
Max Act: 8.7736. Min Act: -0.1700
Data Index: 6017502 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #19