Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2009 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 2.7272. Min Range: -2.7272
Max Act: 2.7272. Min Act: -0.1700
Data Index: 488390 (C4 (Web Text))
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7272. Min Range: -2.7272
Max Act: 2.7112. Min Act: -0.1700
Data Index: 796814 (C4 (Web Text))
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7272. Min Range: -2.7272
Max Act: 2.6952. Min Act: -0.1700
Data Index: 712938 (C4 (Web Text))
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7272. Min Range: -2.7272
Max Act: 2.6952. Min Act: -0.1700
Data Index: 668157 (C4 (Web Text))
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7272. Min Range: -2.7272
Max Act: 2.6792. Min Act: -0.1700
Data Index: 282106 (C4 (Web Text))
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7272. Min Range: -2.7272
Max Act: 2.6471. Min Act: -0.1700
Data Index: 869640 (C4 (Web Text))
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7272. Min Range: -2.7272
Max Act: 2.6631. Min Act: -0.1700
Data Index: 1182504 (C4 (Web Text))
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7272. Min Range: -2.7272
Max Act: 2.6471. Min Act: -0.1700
Data Index: 155578 (C4 (Web Text))
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7272. Min Range: -2.7272
Max Act: 2.6631. Min Act: -0.1700
Data Index: 288753 (C4 (Web Text))
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7272. Min Range: -2.7272
Max Act: 2.6310. Min Act: -0.1700
Data Index: 605797 (C4 (Web Text))
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7272. Min Range: -2.7272
Max Act: 2.6310. Min Act: -0.1700
Data Index: 654154 (C4 (Web Text))
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7272. Min Range: -2.7272
Max Act: 2.5989. Min Act: -0.1700
Data Index: 333404 (C4 (Web Text))
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7272. Min Range: -2.7272
Max Act: 2.5989. Min Act: -0.1700
Data Index: 660915 (C4 (Web Text))
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7272. Min Range: -2.7272
Max Act: 2.6150. Min Act: -0.1700
Data Index: 693161 (C4 (Web Text))
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7272. Min Range: -2.7272
Max Act: 2.6150. Min Act: -0.1700
Data Index: 839906 (C4 (Web Text))
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7272. Min Range: -2.7272
Max Act: 2.5989. Min Act: -0.1700
Data Index: 462285 (C4 (Web Text))
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7272. Min Range: -2.7272
Max Act: 2.5989. Min Act: -0.1700
Data Index: 114892 (C4 (Web Text))
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7272. Min Range: -2.7272
Max Act: 2.5828. Min Act: -0.1700
Data Index: 325691 (C4 (Web Text))
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7272. Min Range: -2.7272
Max Act: 2.6150. Min Act: -0.1700
Data Index: 240750 (C4 (Web Text))
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7272. Min Range: -2.7272
Max Act: 2.5828. Min Act: -0.1700
Data Index: 289604 (C4 (Web Text))
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #19