Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1401 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.0905. Min Range: -8.0905
Max Act: 8.0905. Min Act: -0.1700
Data Index: 715773 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0905. Min Range: -8.0905
Max Act: 7.8718. Min Act: -0.1700
Data Index: 3882584 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0905. Min Range: -8.0905
Max Act: 7.8718. Min Act: -0.1700
Data Index: 7571792 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0905. Min Range: -8.0905
Max Act: 7.8405. Min Act: -0.1700
Data Index: 4012133 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0905. Min Range: -8.0905
Max Act: 7.7468. Min Act: -0.1700
Data Index: 2524367 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0905. Min Range: -8.0905
Max Act: 7.7155. Min Act: -0.1700
Data Index: 6504458 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0905. Min Range: -8.0905
Max Act: 7.7468. Min Act: -0.1700
Data Index: 1343634 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0905. Min Range: -8.0905
Max Act: 7.7468. Min Act: -0.1700
Data Index: 93208 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0905. Min Range: -8.0905
Max Act: 7.7155. Min Act: -0.1700
Data Index: 5913415 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0905. Min Range: -8.0905
Max Act: 7.6843. Min Act: -0.1700
Data Index: 6941902 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0905. Min Range: -8.0905
Max Act: 7.6843. Min Act: -0.1700
Data Index: 719405 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0905. Min Range: -8.0905
Max Act: 7.6843. Min Act: -0.1700
Data Index: 3109209 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0905. Min Range: -8.0905
Max Act: 7.6843. Min Act: -0.1700
Data Index: 4443192 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0905. Min Range: -8.0905
Max Act: 7.6530. Min Act: -0.1700
Data Index: 2923011 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0905. Min Range: -8.0905
Max Act: 7.6530. Min Act: -0.1700
Data Index: 2955044 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0905. Min Range: -8.0905
Max Act: 7.6530. Min Act: -0.1700
Data Index: 4847421 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0905. Min Range: -8.0905
Max Act: 7.6218. Min Act: -0.1700
Data Index: 765007 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0905. Min Range: -8.0905
Max Act: 7.6218. Min Act: -0.1700
Data Index: 7638717 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0905. Min Range: -8.0905
Max Act: 7.5905. Min Act: -0.1700
Data Index: 6229597 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0905. Min Range: -8.0905
Max Act: 7.6218. Min Act: -0.1700
Data Index: 3873900 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #19