Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1970 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.9689. Min Range: -6.9689
Max Act: 6.9689. Min Act: -0.1700
Data Index: 5975294 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9689. Min Range: -6.9689
Max Act: 6.3752. Min Act: -0.1700
Data Index: 5616281 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9689. Min Range: -6.9689
Max Act: 6.3439. Min Act: -0.1700
Data Index: 279780 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9689. Min Range: -6.9689
Max Act: 6.2814. Min Act: -0.1700
Data Index: 2481704 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9689. Min Range: -6.9689
Max Act: 6.2814. Min Act: -0.1700
Data Index: 4487884 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9689. Min Range: -6.9689
Max Act: 6.1877. Min Act: -0.1700
Data Index: 6061623 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9689. Min Range: -6.9689
Max Act: 6.1877. Min Act: -0.1700
Data Index: 3616270 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9689. Min Range: -6.9689
Max Act: 6.1564. Min Act: -0.1700
Data Index: 8464640 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9689. Min Range: -6.9689
Max Act: 6.1252. Min Act: -0.1700
Data Index: 443939 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9689. Min Range: -6.9689
Max Act: 6.1252. Min Act: -0.1700
Data Index: 2642208 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9689. Min Range: -6.9689
Max Act: 6.1252. Min Act: -0.1700
Data Index: 6133951 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9689. Min Range: -6.9689
Max Act: 6.0939. Min Act: -0.1700
Data Index: 8730585 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9689. Min Range: -6.9689
Max Act: 6.1252. Min Act: -0.1700
Data Index: 6434366 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9689. Min Range: -6.9689
Max Act: 6.0939. Min Act: -0.1700
Data Index: 7647414 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9689. Min Range: -6.9689
Max Act: 6.0939. Min Act: -0.1700
Data Index: 6875060 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9689. Min Range: -6.9689
Max Act: 6.0627. Min Act: -0.1700
Data Index: 2132196 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9689. Min Range: -6.9689
Max Act: 6.0627. Min Act: -0.1700
Data Index: 6357930 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9689. Min Range: -6.9689
Max Act: 6.0627. Min Act: -0.1700
Data Index: 7009918 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9689. Min Range: -6.9689
Max Act: 6.0627. Min Act: -0.1700
Data Index: 1530467 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9689. Min Range: -6.9689
Max Act: 6.0627. Min Act: -0.1700
Data Index: 4364898 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #19