Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1016 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 3.0058. Min Range: -3.0058
Max Act: 3.0058. Min Act: -0.1700
Data Index: 587065 (C4 (Web Text))
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0058. Min Range: -3.0058
Max Act: 2.9742. Min Act: -0.1700
Data Index: 135231 (C4 (Web Text))
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0058. Min Range: -3.0058
Max Act: 2.9425. Min Act: -0.1700
Data Index: 205298 (C4 (Web Text))
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0058. Min Range: -3.0058
Max Act: 2.9108. Min Act: -0.1700
Data Index: 446113 (C4 (Web Text))
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0058. Min Range: -3.0058
Max Act: 2.7518. Min Act: -0.1700
Data Index: 1331981 (C4 (Web Text))
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0058. Min Range: -3.0058
Max Act: 2.7198. Min Act: -0.1700
Data Index: 882246 (C4 (Web Text))
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0058. Min Range: -3.0058
Max Act: 2.7198. Min Act: -0.1700
Data Index: 13627 (C4 (Web Text))
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0058. Min Range: -3.0058
Max Act: 2.6878. Min Act: -0.1700
Data Index: 805894 (C4 (Web Text))
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0058. Min Range: -3.0058
Max Act: 2.6878. Min Act: -0.1700
Data Index: 321375 (C4 (Web Text))
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0058. Min Range: -3.0058
Max Act: 2.6718. Min Act: -0.1700
Data Index: 413654 (C4 (Web Text))
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0058. Min Range: -3.0058
Max Act: 2.6558. Min Act: -0.1700
Data Index: 378843 (C4 (Web Text))
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0058. Min Range: -3.0058
Max Act: 2.6718. Min Act: -0.1700
Data Index: 1315823 (C4 (Web Text))
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0058. Min Range: -3.0058
Max Act: 2.6397. Min Act: -0.1700
Data Index: 367784 (C4 (Web Text))
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0058. Min Range: -3.0058
Max Act: 2.6558. Min Act: -0.1700
Data Index: 286932 (C4 (Web Text))
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0058. Min Range: -3.0058
Max Act: 2.6558. Min Act: -0.1700
Data Index: 27913 (C4 (Web Text))
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0058. Min Range: -3.0058
Max Act: 2.6397. Min Act: -0.1700
Data Index: 962502 (C4 (Web Text))
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0058. Min Range: -3.0058
Max Act: 2.6397. Min Act: -0.1700
Data Index: 979667 (C4 (Web Text))
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0058. Min Range: -3.0058
Max Act: 2.6397. Min Act: -0.1700
Data Index: 726281 (C4 (Web Text))
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0058. Min Range: -3.0058
Max Act: 2.6237. Min Act: -0.1700
Data Index: 1063193 (C4 (Web Text))
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0058. Min Range: -3.0058
Max Act: 2.6076. Min Act: -0.1700
Data Index: 156670 (C4 (Web Text))
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #19