Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2350 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 9.0051. Min Range: -9.0051
Max Act: 9.0051. Min Act: -0.1700
Data Index: 702280 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.0051. Min Range: -9.0051
Max Act: 8.8801. Min Act: -0.1700
Data Index: 2147674 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.0051. Min Range: -9.0051
Max Act: 8.8801. Min Act: -0.1700
Data Index: 6163235 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.0051. Min Range: -9.0051
Max Act: 8.8176. Min Act: -0.1700
Data Index: 1387472 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.0051. Min Range: -9.0051
Max Act: 8.7551. Min Act: -0.1700
Data Index: 6501489 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.0051. Min Range: -9.0051
Max Act: 8.7551. Min Act: -0.1700
Data Index: 5914137 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.0051. Min Range: -9.0051
Max Act: 8.7551. Min Act: -0.1700
Data Index: 5054257 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.0051. Min Range: -9.0051
Max Act: 8.7551. Min Act: -0.1700
Data Index: 7556474 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.0051. Min Range: -9.0051
Max Act: 8.6926. Min Act: -0.1700
Data Index: 6272418 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.0051. Min Range: -9.0051
Max Act: 8.6926. Min Act: -0.1700
Data Index: 6651418 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.0051. Min Range: -9.0051
Max Act: 8.6301. Min Act: -0.1700
Data Index: 67913 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.0051. Min Range: -9.0051
Max Act: 8.6301. Min Act: -0.1700
Data Index: 6067166 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.0051. Min Range: -9.0051
Max Act: 8.5676. Min Act: -0.1700
Data Index: 5638896 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.0051. Min Range: -9.0051
Max Act: 8.5676. Min Act: -0.1700
Data Index: 1538041 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.0051. Min Range: -9.0051
Max Act: 8.5676. Min Act: -0.1700
Data Index: 370242 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.0051. Min Range: -9.0051
Max Act: 8.5676. Min Act: -0.1700
Data Index: 1744321 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.0051. Min Range: -9.0051
Max Act: 8.5676. Min Act: -0.1700
Data Index: 584774 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.0051. Min Range: -9.0051
Max Act: 8.5676. Min Act: -0.1700
Data Index: 6062484 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.0051. Min Range: -9.0051
Max Act: 8.5676. Min Act: -0.1700
Data Index: 385948 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.0051. Min Range: -9.0051
Max Act: 8.5676. Min Act: -0.1700
Data Index: 4185061 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #19