Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 31 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 4.7665. Min Range: -4.7665
Max Act: 4.7665. Min Act: -0.1700
Data Index: 1111747 (C4 (Web Text))
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7665. Min Range: -4.7665
Max Act: 4.7040. Min Act: -0.1700
Data Index: 806281 (C4 (Web Text))
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7665. Min Range: -4.7665
Max Act: 4.6727. Min Act: -0.1700
Data Index: 561087 (C4 (Web Text))
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7665. Min Range: -4.7665
Max Act: 4.7352. Min Act: -0.1700
Data Index: 94705 (C4 (Web Text))
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7665. Min Range: -4.7665
Max Act: 4.6727. Min Act: -0.1700
Data Index: 185006 (C4 (Web Text))
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7665. Min Range: -4.7665
Max Act: 4.6727. Min Act: -0.1700
Data Index: 1328495 (C4 (Web Text))
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7665. Min Range: -4.7665
Max Act: 4.6415. Min Act: -0.1700
Data Index: 618877 (C4 (Web Text))
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7665. Min Range: -4.7665
Max Act: 4.6727. Min Act: -0.1700
Data Index: 457222 (C4 (Web Text))
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7665. Min Range: -4.7665
Max Act: 4.6727. Min Act: -0.1700
Data Index: 136951 (C4 (Web Text))
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7665. Min Range: -4.7665
Max Act: 4.7040. Min Act: -0.1700
Data Index: 1010701 (C4 (Web Text))
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7665. Min Range: -4.7665
Max Act: 4.6415. Min Act: -0.1700
Data Index: 978513 (C4 (Web Text))
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7665. Min Range: -4.7665
Max Act: 4.6727. Min Act: -0.1700
Data Index: 542667 (C4 (Web Text))
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7665. Min Range: -4.7665
Max Act: 4.6102. Min Act: -0.1700
Data Index: 234057 (C4 (Web Text))
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7665. Min Range: -4.7665
Max Act: 4.6415. Min Act: -0.1700
Data Index: 679733 (C4 (Web Text))
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7665. Min Range: -4.7665
Max Act: 4.6415. Min Act: -0.1700
Data Index: 1330966 (C4 (Web Text))
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7665. Min Range: -4.7665
Max Act: 4.6727. Min Act: -0.1700
Data Index: 631669 (C4 (Web Text))
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7665. Min Range: -4.7665
Max Act: 4.6102. Min Act: -0.1700
Data Index: 98154 (C4 (Web Text))
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7665. Min Range: -4.7665
Max Act: 4.6102. Min Act: -0.1700
Data Index: 915019 (C4 (Web Text))
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7665. Min Range: -4.7665
Max Act: 4.6415. Min Act: -0.1700
Data Index: 948041 (C4 (Web Text))
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7665. Min Range: -4.7665
Max Act: 4.6102. Min Act: -0.1700
Data Index: 511433 (C4 (Web Text))
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #19