Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3561 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8988. Min Range: -4.8988
Max Act: 4.8988. Min Act: -0.1700
Data Index: 2805769 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8988. Min Range: -4.8988
Max Act: 4.8363. Min Act: -0.1700
Data Index: 3706998 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8988. Min Range: -4.8988
Max Act: 4.8051. Min Act: -0.1700
Data Index: 648790 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8988. Min Range: -4.8988
Max Act: 4.7738. Min Act: -0.1700
Data Index: 7548951 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8988. Min Range: -4.8988
Max Act: 4.7426. Min Act: -0.1700
Data Index: 7964232 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8988. Min Range: -4.8988
Max Act: 4.6801. Min Act: -0.1700
Data Index: 4239177 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8988. Min Range: -4.8988
Max Act: 4.6801. Min Act: -0.1700
Data Index: 115383 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8988. Min Range: -4.8988
Max Act: 4.6488. Min Act: -0.1700
Data Index: 4569968 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8988. Min Range: -4.8988
Max Act: 4.6176. Min Act: -0.1700
Data Index: 5944993 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8988. Min Range: -4.8988
Max Act: 4.6176. Min Act: -0.1700
Data Index: 1854489 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8988. Min Range: -4.8988
Max Act: 4.6176. Min Act: -0.1700
Data Index: 3751044 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8988. Min Range: -4.8988
Max Act: 4.6176. Min Act: -0.1700
Data Index: 1642289 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8988. Min Range: -4.8988
Max Act: 4.5863. Min Act: -0.1700
Data Index: 6300838 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8988. Min Range: -4.8988
Max Act: 4.5863. Min Act: -0.1700
Data Index: 6826786 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8988. Min Range: -4.8988
Max Act: 4.6176. Min Act: -0.1700
Data Index: 4633244 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8988. Min Range: -4.8988
Max Act: 4.5551. Min Act: -0.1700
Data Index: 774500 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8988. Min Range: -4.8988
Max Act: 4.5551. Min Act: -0.1700
Data Index: 2274849 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8988. Min Range: -4.8988
Max Act: 4.5551. Min Act: -0.1700
Data Index: 7155727 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8988. Min Range: -4.8988
Max Act: 4.5551. Min Act: -0.1700
Data Index: 3959879 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8988. Min Range: -4.8988
Max Act: 4.5551. Min Act: -0.1700
Data Index: 4162738 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #19