Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 456 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0756. Min Range: -4.0756
Max Act: 4.0756. Min Act: -0.1700
Data Index: 5028875 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0756. Min Range: -4.0756
Max Act: 4.0443. Min Act: -0.1700
Data Index: 3508982 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0756. Min Range: -4.0756
Max Act: 3.9818. Min Act: -0.1700
Data Index: 2557155 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0756. Min Range: -4.0756
Max Act: 3.9818. Min Act: -0.1700
Data Index: 7373314 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0756. Min Range: -4.0756
Max Act: 3.9505. Min Act: -0.1700
Data Index: 3004884 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0756. Min Range: -4.0756
Max Act: 3.9193. Min Act: -0.1700
Data Index: 3434515 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0756. Min Range: -4.0756
Max Act: 3.9505. Min Act: -0.1700
Data Index: 2877733 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0756. Min Range: -4.0756
Max Act: 3.9193. Min Act: -0.1700
Data Index: 1389410 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0756. Min Range: -4.0756
Max Act: 3.9193. Min Act: -0.1700
Data Index: 2487919 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0756. Min Range: -4.0756
Max Act: 3.9193. Min Act: -0.1700
Data Index: 7606109 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0756. Min Range: -4.0756
Max Act: 3.9193. Min Act: -0.1700
Data Index: 4553190 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0756. Min Range: -4.0756
Max Act: 3.8880. Min Act: -0.1700
Data Index: 6212239 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0756. Min Range: -4.0756
Max Act: 3.8567. Min Act: -0.1700
Data Index: 7668822 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0756. Min Range: -4.0756
Max Act: 3.8880. Min Act: -0.1700
Data Index: 5225439 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0756. Min Range: -4.0756
Max Act: 3.8880. Min Act: -0.1700
Data Index: 771146 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0756. Min Range: -4.0756
Max Act: 3.8880. Min Act: -0.1700
Data Index: 779979 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0756. Min Range: -4.0756
Max Act: 3.8880. Min Act: -0.1700
Data Index: 4410555 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0756. Min Range: -4.0756
Max Act: 3.8255. Min Act: -0.1700
Data Index: 936256 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0756. Min Range: -4.0756
Max Act: 3.8255. Min Act: -0.1700
Data Index: 1903134 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0756. Min Range: -4.0756
Max Act: 3.7942. Min Act: -0.1700
Data Index: 1034793 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #19