Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2742 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8117. Min Range: -5.8117
Max Act: 5.8117. Min Act: -0.1700
Data Index: 3943241 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8117. Min Range: -5.8117
Max Act: 5.5617. Min Act: -0.1700
Data Index: 7702199 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8117. Min Range: -5.8117
Max Act: 5.4055. Min Act: -0.1700
Data Index: 69135 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8117. Min Range: -5.8117
Max Act: 5.4680. Min Act: -0.1700
Data Index: 5254338 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8117. Min Range: -5.8117
Max Act: 5.4055. Min Act: -0.1700
Data Index: 4323495 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8117. Min Range: -5.8117
Max Act: 5.4055. Min Act: -0.1698
Data Index: 8770221 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8117. Min Range: -5.8117
Max Act: 5.3430. Min Act: -0.1700
Data Index: 5249895 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8117. Min Range: -5.8117
Max Act: 5.3430. Min Act: -0.1700
Data Index: 5147674 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8117. Min Range: -5.8117
Max Act: 5.3117. Min Act: -0.1700
Data Index: 1138171 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8117. Min Range: -5.8117
Max Act: 5.2805. Min Act: -0.1700
Data Index: 7805079 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8117. Min Range: -5.8117
Max Act: 5.2805. Min Act: -0.1700
Data Index: 5254345 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8117. Min Range: -5.8117
Max Act: 5.2805. Min Act: -0.1700
Data Index: 7960846 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8117. Min Range: -5.8117
Max Act: 5.2492. Min Act: -0.1700
Data Index: 7266075 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8117. Min Range: -5.8117
Max Act: 5.2492. Min Act: -0.1700
Data Index: 5624368 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8117. Min Range: -5.8117
Max Act: 5.2180. Min Act: -0.1700
Data Index: 4241394 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8117. Min Range: -5.8117
Max Act: 5.2492. Min Act: -0.1700
Data Index: 6218601 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8117. Min Range: -5.8117
Max Act: 5.2180. Min Act: -0.1700
Data Index: 845067 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8117. Min Range: -5.8117
Max Act: 5.2180. Min Act: -0.1700
Data Index: 338083 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8117. Min Range: -5.8117
Max Act: 5.2180. Min Act: -0.1700
Data Index: 5707705 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8117. Min Range: -5.8117
Max Act: 5.1867. Min Act: -0.1700
Data Index: 2181811 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #19