Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1949 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 4.9077. Min Range: -4.9077
Max Act: 4.9077. Min Act: -0.1700
Data Index: 1333584 (C4 (Web Text))
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9077. Min Range: -4.9077
Max Act: 4.8452. Min Act: -0.1700
Data Index: 737475 (C4 (Web Text))
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9077. Min Range: -4.9077
Max Act: 4.8139. Min Act: -0.1700
Data Index: 702506 (C4 (Web Text))
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9077. Min Range: -4.9077
Max Act: 4.7827. Min Act: -0.1700
Data Index: 331469 (C4 (Web Text))
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9077. Min Range: -4.9077
Max Act: 4.7827. Min Act: -0.1700
Data Index: 275431 (C4 (Web Text))
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9077. Min Range: -4.9077
Max Act: 4.7202. Min Act: -0.1700
Data Index: 565505 (C4 (Web Text))
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9077. Min Range: -4.9077
Max Act: 4.7514. Min Act: -0.1700
Data Index: 653020 (C4 (Web Text))
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9077. Min Range: -4.9077
Max Act: 4.7202. Min Act: -0.1700
Data Index: 657043 (C4 (Web Text))
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9077. Min Range: -4.9077
Max Act: 4.7202. Min Act: -0.1700
Data Index: 281887 (C4 (Web Text))
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9077. Min Range: -4.9077
Max Act: 4.6889. Min Act: -0.1700
Data Index: 400292 (C4 (Web Text))
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9077. Min Range: -4.9077
Max Act: 4.6889. Min Act: -0.1700
Data Index: 990709 (C4 (Web Text))
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9077. Min Range: -4.9077
Max Act: 4.6889. Min Act: -0.1700
Data Index: 1228580 (C4 (Web Text))
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9077. Min Range: -4.9077
Max Act: 4.7202. Min Act: -0.1700
Data Index: 749236 (C4 (Web Text))
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9077. Min Range: -4.9077
Max Act: 4.6889. Min Act: -0.1700
Data Index: 806163 (C4 (Web Text))
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9077. Min Range: -4.9077
Max Act: 4.6577. Min Act: -0.1700
Data Index: 220643 (C4 (Web Text))
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9077. Min Range: -4.9077
Max Act: 4.6889. Min Act: -0.1700
Data Index: 970933 (C4 (Web Text))
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9077. Min Range: -4.9077
Max Act: 4.6889. Min Act: -0.1700
Data Index: 525040 (C4 (Web Text))
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9077. Min Range: -4.9077
Max Act: 4.6577. Min Act: -0.1700
Data Index: 1062571 (C4 (Web Text))
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9077. Min Range: -4.9077
Max Act: 4.6889. Min Act: -0.1700
Data Index: 487898 (C4 (Web Text))
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9077. Min Range: -4.9077
Max Act: 4.6577. Min Act: -0.1700
Data Index: 779381 (C4 (Web Text))
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #19