Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 642 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 3.2007. Min Range: -3.2007
Max Act: 3.2007. Min Act: -0.1700
Data Index: 1012756 (C4 (Web Text))
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2007. Min Range: -3.2007
Max Act: 3.1849. Min Act: -0.1700
Data Index: 419563 (C4 (Web Text))
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2007. Min Range: -3.2007
Max Act: 3.1849. Min Act: -0.1700
Data Index: 189946 (C4 (Web Text))
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2007. Min Range: -3.2007
Max Act: 3.1692. Min Act: -0.1700
Data Index: 20073 (C4 (Web Text))
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2007. Min Range: -3.2007
Max Act: 3.1849. Min Act: -0.1700
Data Index: 431684 (C4 (Web Text))
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2007. Min Range: -3.2007
Max Act: 3.1692. Min Act: -0.1700
Data Index: 776649 (C4 (Web Text))
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2007. Min Range: -3.2007
Max Act: 3.1534. Min Act: -0.1700
Data Index: 817719 (C4 (Web Text))
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2007. Min Range: -3.2007
Max Act: 3.1849. Min Act: -0.1700
Data Index: 26960 (C4 (Web Text))
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2007. Min Range: -3.2007
Max Act: 3.1692. Min Act: -0.1700
Data Index: 624422 (C4 (Web Text))
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2007. Min Range: -3.2007
Max Act: 3.1849. Min Act: -0.1700
Data Index: 587444 (C4 (Web Text))
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2007. Min Range: -3.2007
Max Act: 3.1692. Min Act: -0.1700
Data Index: 428381 (C4 (Web Text))
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2007. Min Range: -3.2007
Max Act: 3.1849. Min Act: -0.1700
Data Index: 976985 (C4 (Web Text))
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2007. Min Range: -3.2007
Max Act: 3.1377. Min Act: -0.1700
Data Index: 10968 (C4 (Web Text))
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2007. Min Range: -3.2007
Max Act: 3.1377. Min Act: -0.1700
Data Index: 191041 (C4 (Web Text))
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2007. Min Range: -3.2007
Max Act: 3.1534. Min Act: -0.1700
Data Index: 685604 (C4 (Web Text))
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2007. Min Range: -3.2007
Max Act: 3.1534. Min Act: -0.1700
Data Index: 104162 (C4 (Web Text))
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2007. Min Range: -3.2007
Max Act: 3.1534. Min Act: -0.1700
Data Index: 295765 (C4 (Web Text))
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2007. Min Range: -3.2007
Max Act: 3.1534. Min Act: -0.1700
Data Index: 514612 (C4 (Web Text))
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2007. Min Range: -3.2007
Max Act: 3.1534. Min Act: -0.1700
Data Index: 593697 (C4 (Web Text))
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2007. Min Range: -3.2007
Max Act: 3.1377. Min Act: -0.1700
Data Index: 563441 (C4 (Web Text))
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #19