Model: GELU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 48 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')
Text #0
Max Range: 2.3272. Min Range: -2.3272
Max Act: 2.3272. Min Act: -0.1692
Data Index: 173010 (C4 (Web Text))
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.3272. Min Range: -2.3272
Max Act: 2.3108. Min Act: -0.1700
Data Index: 721889 (C4 (Web Text))
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.3272. Min Range: -2.3272
Max Act: 2.3108. Min Act: -0.1698
Data Index: 866978 (C4 (Web Text))
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.3272. Min Range: -2.3272
Max Act: 2.3108. Min Act: -0.1700
Data Index: 1293339 (C4 (Web Text))
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.3272. Min Range: -2.3272
Max Act: 2.3108. Min Act: -0.1698
Data Index: 1069908 (C4 (Web Text))
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.3272. Min Range: -2.3272
Max Act: 2.3108. Min Act: -0.1700
Data Index: 381949 (C4 (Web Text))
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.3272. Min Range: -2.3272
Max Act: 2.3108. Min Act: -0.1700
Data Index: 1034088 (C4 (Web Text))
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.3272. Min Range: -2.3272
Max Act: 2.3108. Min Act: -0.1698
Data Index: 1220863 (C4 (Web Text))
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.3272. Min Range: -2.3272
Max Act: 2.2943. Min Act: -0.1700
Data Index: 209272 (C4 (Web Text))
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.3272. Min Range: -2.3272
Max Act: 2.2943. Min Act: -0.1699
Data Index: 1086987 (C4 (Web Text))
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.3272. Min Range: -2.3272
Max Act: 2.2779. Min Act: -0.1699
Data Index: 539508 (C4 (Web Text))
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.3272. Min Range: -2.3272
Max Act: 2.2943. Min Act: -0.1699
Data Index: 709158 (C4 (Web Text))
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.3272. Min Range: -2.3272
Max Act: 2.3108. Min Act: -0.1700
Data Index: 1355859 (C4 (Web Text))
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.3272. Min Range: -2.3272
Max Act: 2.2779. Min Act: -0.1700
Data Index: 592264 (C4 (Web Text))
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.3272. Min Range: -2.3272
Max Act: 2.2779. Min Act: -0.1700
Data Index: 616993 (C4 (Web Text))
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.3272. Min Range: -2.3272
Max Act: 2.2779. Min Act: -0.1700
Data Index: 220510 (C4 (Web Text))
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.3272. Min Range: -2.3272
Max Act: 2.2614. Min Act: -0.1699
Data Index: 1237713 (C4 (Web Text))
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.3272. Min Range: -2.3272
Max Act: 2.2779. Min Act: -0.1700
Data Index: 816358 (C4 (Web Text))
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.3272. Min Range: -2.3272
Max Act: 2.2779. Min Act: -0.1700
Data Index: 1135873 (C4 (Web Text))
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.3272. Min Range: -2.3272
Max Act: 2.2779. Min Act: -0.1696
Data Index: 583879 (C4 (Web Text))
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #19