Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1078 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 6.2668. Min Range: -6.2668
Max Act: 6.2668. Min Act: -0.1700
Data Index: 147656 (C4 (Web Text))
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2668. Min Range: -6.2668
Max Act: 5.9231. Min Act: -0.1700
Data Index: 372803 (C4 (Web Text))
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2668. Min Range: -6.2668
Max Act: 5.8918. Min Act: -0.1700
Data Index: 748215 (C4 (Web Text))
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2668. Min Range: -6.2668
Max Act: 5.8918. Min Act: -0.1700
Data Index: 286880 (C4 (Web Text))
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2668. Min Range: -6.2668
Max Act: 5.8293. Min Act: -0.1700
Data Index: 820125 (C4 (Web Text))
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2668. Min Range: -6.2668
Max Act: 5.8293. Min Act: -0.1700
Data Index: 396506 (C4 (Web Text))
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2668. Min Range: -6.2668
Max Act: 5.8293. Min Act: -0.1700
Data Index: 204776 (C4 (Web Text))
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2668. Min Range: -6.2668
Max Act: 5.8293. Min Act: -0.1700
Data Index: 586695 (C4 (Web Text))
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2668. Min Range: -6.2668
Max Act: 5.8918. Min Act: -0.1700
Data Index: 416639 (C4 (Web Text))
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2668. Min Range: -6.2668
Max Act: 5.7981. Min Act: -0.1700
Data Index: 901503 (C4 (Web Text))
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2668. Min Range: -6.2668
Max Act: 5.7668. Min Act: -0.1700
Data Index: 327860 (C4 (Web Text))
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2668. Min Range: -6.2668
Max Act: 5.7981. Min Act: -0.1700
Data Index: 355016 (C4 (Web Text))
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2668. Min Range: -6.2668
Max Act: 5.8293. Min Act: -0.1700
Data Index: 119908 (C4 (Web Text))
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2668. Min Range: -6.2668
Max Act: 5.8606. Min Act: -0.1700
Data Index: 586264 (C4 (Web Text))
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2668. Min Range: -6.2668
Max Act: 5.8606. Min Act: -0.1700
Data Index: 1239885 (C4 (Web Text))
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2668. Min Range: -6.2668
Max Act: 5.8606. Min Act: -0.1700
Data Index: 436462 (C4 (Web Text))
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2668. Min Range: -6.2668
Max Act: 5.7668. Min Act: -0.1700
Data Index: 94493 (C4 (Web Text))
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2668. Min Range: -6.2668
Max Act: 5.7043. Min Act: -0.1700
Data Index: 960996 (C4 (Web Text))
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2668. Min Range: -6.2668
Max Act: 5.7981. Min Act: -0.1700
Data Index: 444561 (C4 (Web Text))
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2668. Min Range: -6.2668
Max Act: 5.7668. Min Act: -0.1700
Data Index: 192329 (C4 (Web Text))
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #19