Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 23 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0829. Min Range: -8.0829
Max Act: 8.0829. Min Act: -0.1700
Data Index: 3053375 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0829. Min Range: -8.0829
Max Act: 8.0204. Min Act: -0.1700
Data Index: 5229903 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0829. Min Range: -8.0829
Max Act: 7.7704. Min Act: -0.1700
Data Index: 635414 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0829. Min Range: -8.0829
Max Act: 7.7079. Min Act: -0.1700
Data Index: 3803826 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0829. Min Range: -8.0829
Max Act: 7.7391. Min Act: -0.1700
Data Index: 4390773 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0829. Min Range: -8.0829
Max Act: 7.7391. Min Act: -0.1700
Data Index: 5555810 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0829. Min Range: -8.0829
Max Act: 7.6766. Min Act: -0.1700
Data Index: 6149504 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0829. Min Range: -8.0829
Max Act: 7.6766. Min Act: -0.1700
Data Index: 2901421 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0829. Min Range: -8.0829
Max Act: 7.6141. Min Act: -0.1700
Data Index: 139440 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0829. Min Range: -8.0829
Max Act: 7.6454. Min Act: -0.1700
Data Index: 2307626 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0829. Min Range: -8.0829
Max Act: 7.6141. Min Act: -0.1700
Data Index: 1546948 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0829. Min Range: -8.0829
Max Act: 7.6141. Min Act: -0.1700
Data Index: 3505955 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0829. Min Range: -8.0829
Max Act: 7.5829. Min Act: -0.1700
Data Index: 4700103 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0829. Min Range: -8.0829
Max Act: 7.5516. Min Act: -0.1700
Data Index: 2047780 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0829. Min Range: -8.0829
Max Act: 7.5516. Min Act: -0.1700
Data Index: 6136777 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0829. Min Range: -8.0829
Max Act: 7.5829. Min Act: -0.1700
Data Index: 4412807 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0829. Min Range: -8.0829
Max Act: 7.5204. Min Act: -0.1700
Data Index: 2910854 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0829. Min Range: -8.0829
Max Act: 7.4891. Min Act: -0.1700
Data Index: 1360736 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0829. Min Range: -8.0829
Max Act: 7.5516. Min Act: -0.1700
Data Index: 7891127 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0829. Min Range: -8.0829
Max Act: 7.5204. Min Act: -0.1700
Data Index: 2505234 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #19