Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4947 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.9942. Min Range: -1.9942
Max Act: 1.9942. Min Act: -0.1700
Data Index: 8401600 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.9942. Min Range: -1.9942
Max Act: 1.9518. Min Act: -0.1700
Data Index: 6898534 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.9942. Min Range: -1.9942
Max Act: 1.9348. Min Act: -0.1700
Data Index: 8137091 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.9942. Min Range: -1.9942
Max Act: 1.9008. Min Act: -0.1700
Data Index: 2257935 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.9942. Min Range: -1.9942
Max Act: 1.8922. Min Act: -0.1700
Data Index: 103340 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.9942. Min Range: -1.9942
Max Act: 1.8751. Min Act: -0.1698
Data Index: 6203688 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.9942. Min Range: -1.9942
Max Act: 1.8751. Min Act: -0.1700
Data Index: 4145348 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.9942. Min Range: -1.9942
Max Act: 1.8751. Min Act: -0.1700
Data Index: 1244130 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.9942. Min Range: -1.9942
Max Act: 1.8580. Min Act: -0.1700
Data Index: 4222105 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.9942. Min Range: -1.9942
Max Act: 1.8666. Min Act: -0.1700
Data Index: 2042312 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.9942. Min Range: -1.9942
Max Act: 1.8580. Min Act: -0.1700
Data Index: 7177846 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.9942. Min Range: -1.9942
Max Act: 1.8580. Min Act: -0.1700
Data Index: 5631217 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.9942. Min Range: -1.9942
Max Act: 1.8580. Min Act: -0.1700
Data Index: 5191650 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.9942. Min Range: -1.9942
Max Act: 1.8495. Min Act: -0.1700
Data Index: 7866746 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.9942. Min Range: -1.9942
Max Act: 1.8495. Min Act: -0.1700
Data Index: 4947459 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.9942. Min Range: -1.9942
Max Act: 1.8409. Min Act: -0.1700
Data Index: 7813763 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.9942. Min Range: -1.9942
Max Act: 1.8323. Min Act: -0.1700
Data Index: 5977416 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.9942. Min Range: -1.9942
Max Act: 1.8409. Min Act: -0.1700
Data Index: 416865 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.9942. Min Range: -1.9942
Max Act: 1.8323. Min Act: -0.1700
Data Index: 5305382 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.9942. Min Range: -1.9942
Max Act: 1.8323. Min Act: -0.1700
Data Index: 6229460 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #19