Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4697 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2875. Min Range: -5.2875
Max Act: 5.2875. Min Act: -0.1700
Data Index: 8102413 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2875. Min Range: -5.2875
Max Act: 5.2250. Min Act: -0.1700
Data Index: 5340827 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2875. Min Range: -5.2875
Max Act: 5.0688. Min Act: -0.1700
Data Index: 2585440 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2875. Min Range: -5.2875
Max Act: 5.0375. Min Act: -0.1700
Data Index: 4048885 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2875. Min Range: -5.2875
Max Act: 5.0063. Min Act: -0.1700
Data Index: 3585902 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2875. Min Range: -5.2875
Max Act: 4.9125. Min Act: -0.1700
Data Index: 40407 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2875. Min Range: -5.2875
Max Act: 4.9125. Min Act: -0.1700
Data Index: 2481536 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2875. Min Range: -5.2875
Max Act: 4.9125. Min Act: -0.1700
Data Index: 447685 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2875. Min Range: -5.2875
Max Act: 4.8500. Min Act: -0.1700
Data Index: 3335777 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2875. Min Range: -5.2875
Max Act: 4.8188. Min Act: -0.1700
Data Index: 313235 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2875. Min Range: -5.2875
Max Act: 4.8188. Min Act: -0.1700
Data Index: 5051349 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2875. Min Range: -5.2875
Max Act: 4.8188. Min Act: -0.1700
Data Index: 768455 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2875. Min Range: -5.2875
Max Act: 4.8188. Min Act: -0.1700
Data Index: 8210875 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2875. Min Range: -5.2875
Max Act: 4.7875. Min Act: -0.1700
Data Index: 7775550 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2875. Min Range: -5.2875
Max Act: 4.7875. Min Act: -0.1700
Data Index: 3703737 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2875. Min Range: -5.2875
Max Act: 4.7875. Min Act: -0.1700
Data Index: 3290573 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2875. Min Range: -5.2875
Max Act: 4.7875. Min Act: -0.1700
Data Index: 4481466 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2875. Min Range: -5.2875
Max Act: 4.7563. Min Act: -0.1700
Data Index: 5276573 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2875. Min Range: -5.2875
Max Act: 4.7563. Min Act: -0.1700
Data Index: 2923527 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2875. Min Range: -5.2875
Max Act: 4.7563. Min Act: -0.1700
Data Index: 5713954 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #19