Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4297 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.7025. Min Range: -9.7025
Max Act: 9.7025. Min Act: -0.1700
Data Index: 8182800 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.7025. Min Range: -9.7025
Max Act: 9.5150. Min Act: -0.1700
Data Index: 7487410 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.7025. Min Range: -9.7025
Max Act: 9.3900. Min Act: -0.1700
Data Index: 5457314 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.7025. Min Range: -9.7025
Max Act: 9.3275. Min Act: -0.1700
Data Index: 7487411 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.7025. Min Range: -9.7025
Max Act: 9.1400. Min Act: -0.1700
Data Index: 2669799 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.7025. Min Range: -9.7025
Max Act: 9.1400. Min Act: -0.1700
Data Index: 4165390 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.7025. Min Range: -9.7025
Max Act: 8.9525. Min Act: -0.1700
Data Index: 4159766 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.7025. Min Range: -9.7025
Max Act: 9.0150. Min Act: -0.1700
Data Index: 4407820 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.7025. Min Range: -9.7025
Max Act: 8.9525. Min Act: -0.1700
Data Index: 7717506 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.7025. Min Range: -9.7025
Max Act: 8.9525. Min Act: -0.1700
Data Index: 4159764 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.7025. Min Range: -9.7025
Max Act: 8.8900. Min Act: -0.1700
Data Index: 135919 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.7025. Min Range: -9.7025
Max Act: 8.8275. Min Act: -0.1700
Data Index: 835150 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.7025. Min Range: -9.7025
Max Act: 8.8275. Min Act: -0.1700
Data Index: 5697715 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.7025. Min Range: -9.7025
Max Act: 8.8275. Min Act: -0.1700
Data Index: 451598 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.7025. Min Range: -9.7025
Max Act: 8.8275. Min Act: -0.1700
Data Index: 624146 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.7025. Min Range: -9.7025
Max Act: 8.7650. Min Act: -0.1700
Data Index: 569994 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.7025. Min Range: -9.7025
Max Act: 8.7650. Min Act: -0.1700
Data Index: 5891441 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.7025. Min Range: -9.7025
Max Act: 8.7650. Min Act: -0.1700
Data Index: 7650688 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.7025. Min Range: -9.7025
Max Act: 8.7650. Min Act: -0.1700
Data Index: 4159765 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.7025. Min Range: -9.7025
Max Act: 8.6400. Min Act: -0.1700
Data Index: 3630727 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #19