Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 251 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.5616. Min Range: -4.5616
Max Act: 4.5616. Min Act: -0.1700
Data Index: 316856 (C4 (Web Text))
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5616. Min Range: -4.5616
Max Act: 4.4678. Min Act: -0.1700
Data Index: 1251957 (C4 (Web Text))
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5616. Min Range: -4.5616
Max Act: 4.4991. Min Act: -0.1700
Data Index: 1179722 (C4 (Web Text))
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5616. Min Range: -4.5616
Max Act: 4.4991. Min Act: -0.1700
Data Index: 159870 (C4 (Web Text))
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5616. Min Range: -4.5616
Max Act: 4.5303. Min Act: -0.1700
Data Index: 450051 (C4 (Web Text))
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5616. Min Range: -4.5616
Max Act: 4.5303. Min Act: -0.1700
Data Index: 418871 (C4 (Web Text))
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5616. Min Range: -4.5616
Max Act: 4.5303. Min Act: -0.1700
Data Index: 781637 (C4 (Web Text))
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5616. Min Range: -4.5616
Max Act: 4.4366. Min Act: -0.1700
Data Index: 444547 (C4 (Web Text))
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5616. Min Range: -4.5616
Max Act: 4.4678. Min Act: -0.1700
Data Index: 478663 (C4 (Web Text))
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5616. Min Range: -4.5616
Max Act: 4.4991. Min Act: -0.1700
Data Index: 702917 (C4 (Web Text))
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5616. Min Range: -4.5616
Max Act: 4.4991. Min Act: -0.1700
Data Index: 80536 (C4 (Web Text))
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5616. Min Range: -4.5616
Max Act: 4.4678. Min Act: -0.1700
Data Index: 1080681 (C4 (Web Text))
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5616. Min Range: -4.5616
Max Act: 4.4991. Min Act: -0.1700
Data Index: 692724 (C4 (Web Text))
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5616. Min Range: -4.5616
Max Act: 4.4678. Min Act: -0.1700
Data Index: 304348 (C4 (Web Text))
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5616. Min Range: -4.5616
Max Act: 4.4366. Min Act: -0.1700
Data Index: 163295 (C4 (Web Text))
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5616. Min Range: -4.5616
Max Act: 4.4366. Min Act: -0.1700
Data Index: 1053651 (C4 (Web Text))
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5616. Min Range: -4.5616
Max Act: 4.4366. Min Act: -0.1700
Data Index: 323844 (C4 (Web Text))
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5616. Min Range: -4.5616
Max Act: 4.4678. Min Act: -0.1700
Data Index: 432209 (C4 (Web Text))
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5616. Min Range: -4.5616
Max Act: 4.4678. Min Act: -0.1700
Data Index: 258837 (C4 (Web Text))
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5616. Min Range: -4.5616
Max Act: 4.4678. Min Act: -0.1700
Data Index: 1144307 (C4 (Web Text))
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #19