Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2441 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.9780. Min Range: -8.9780
Max Act: 8.9780. Min Act: -0.1700
Data Index: 7932743 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.9780. Min Range: -8.9780
Max Act: 8.7905. Min Act: -0.1700
Data Index: 795436 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.9780. Min Range: -8.9780
Max Act: 8.6655. Min Act: -0.1700
Data Index: 5910909 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.9780. Min Range: -8.9780
Max Act: 8.4155. Min Act: -0.1700
Data Index: 7419223 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.9780. Min Range: -8.9780
Max Act: 8.4155. Min Act: -0.1700
Data Index: 2469006 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.9780. Min Range: -8.9780
Max Act: 8.2905. Min Act: -0.1700
Data Index: 1697534 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.9780. Min Range: -8.9780
Max Act: 8.1030. Min Act: -0.1700
Data Index: 2469005 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.9780. Min Range: -8.9780
Max Act: 8.1030. Min Act: -0.1700
Data Index: 5119965 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.9780. Min Range: -8.9780
Max Act: 8.0405. Min Act: -0.1700
Data Index: 3858712 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.9780. Min Range: -8.9780
Max Act: 8.0405. Min Act: -0.1700
Data Index: 106180 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.9780. Min Range: -8.9780
Max Act: 8.0405. Min Act: -0.1700
Data Index: 5626232 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.9780. Min Range: -8.9780
Max Act: 7.9780. Min Act: -0.1700
Data Index: 274120 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.9780. Min Range: -8.9780
Max Act: 7.9780. Min Act: -0.1700
Data Index: 8647609 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.9780. Min Range: -8.9780
Max Act: 7.9155. Min Act: -0.1700
Data Index: 734764 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.9780. Min Range: -8.9780
Max Act: 7.9155. Min Act: -0.1700
Data Index: 5823161 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.9780. Min Range: -8.9780
Max Act: 7.8530. Min Act: -0.1700
Data Index: 6328771 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.9780. Min Range: -8.9780
Max Act: 7.7905. Min Act: -0.1700
Data Index: 4789927 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.9780. Min Range: -8.9780
Max Act: 7.7905. Min Act: -0.1700
Data Index: 5004241 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.9780. Min Range: -8.9780
Max Act: 7.7905. Min Act: -0.1700
Data Index: 1718088 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.9780. Min Range: -8.9780
Max Act: 7.7905. Min Act: -0.1700
Data Index: 7125004 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #19