Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6360 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.1028. Min Range: -3.1028
Max Act: 3.1028. Min Act: -0.1700
Data Index: 645345 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1028. Min Range: -3.1028
Max Act: 3.0870. Min Act: -0.1700
Data Index: 3684829 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1028. Min Range: -3.1028
Max Act: 3.0555. Min Act: -0.1700
Data Index: 3684827 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1028. Min Range: -3.1028
Max Act: 3.0555. Min Act: -0.1700
Data Index: 3684828 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1028. Min Range: -3.1028
Max Act: 3.0239. Min Act: -0.1700
Data Index: 1038951 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1028. Min Range: -3.1028
Max Act: 3.0081. Min Act: -0.1700
Data Index: 4335895 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1028. Min Range: -3.1028
Max Act: 3.0081. Min Act: -0.1700
Data Index: 298923 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1028. Min Range: -3.1028
Max Act: 3.0081. Min Act: -0.1700
Data Index: 8771426 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1028. Min Range: -3.1028
Max Act: 2.9923. Min Act: -0.1700
Data Index: 8137153 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1028. Min Range: -3.1028
Max Act: 2.9923. Min Act: -0.1700
Data Index: 225452 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1028. Min Range: -3.1028
Max Act: 2.9923. Min Act: -0.1700
Data Index: 4219309 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1028. Min Range: -3.1028
Max Act: 2.9923. Min Act: -0.1700
Data Index: 8602353 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1028. Min Range: -3.1028
Max Act: 2.9923. Min Act: -0.1700
Data Index: 7363682 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1028. Min Range: -3.1028
Max Act: 2.9923. Min Act: -0.1700
Data Index: 7030727 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1028. Min Range: -3.1028
Max Act: 2.9923. Min Act: -0.1700
Data Index: 3966236 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1028. Min Range: -3.1028
Max Act: 2.9923. Min Act: -0.1700
Data Index: 6127579 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1028. Min Range: -3.1028
Max Act: 2.9765. Min Act: -0.1700
Data Index: 7488849 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1028. Min Range: -3.1028
Max Act: 2.9923. Min Act: -0.1700
Data Index: 1897134 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1028. Min Range: -3.1028
Max Act: 2.9765. Min Act: -0.1700
Data Index: 4864080 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1028. Min Range: -3.1028
Max Act: 2.9765. Min Act: -0.1700
Data Index: 7857957 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #19