Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1024 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 2.4987. Min Range: -2.4987
Max Act: 2.4987. Min Act: -0.1700
Data Index: 525648 (C4 (Web Text))
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.4987. Min Range: -2.4987
Max Act: 2.4012. Min Act: -0.1700
Data Index: 996314 (C4 (Web Text))
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.4987. Min Range: -2.4987
Max Act: 2.3848. Min Act: -0.1700
Data Index: 713977 (C4 (Web Text))
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.4987. Min Range: -2.4987
Max Act: 2.3848. Min Act: -0.1700
Data Index: 422011 (C4 (Web Text))
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.4987. Min Range: -2.4987
Max Act: 2.3685. Min Act: -0.1700
Data Index: 634967 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.4987. Min Range: -2.4987
Max Act: 2.3685. Min Act: -0.1700
Data Index: 791626 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.4987. Min Range: -2.4987
Max Act: 2.3685. Min Act: -0.1700
Data Index: 1039831 (C4 (Web Text))
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.4987. Min Range: -2.4987
Max Act: 2.3521. Min Act: -0.1700
Data Index: 584163 (C4 (Web Text))
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.4987. Min Range: -2.4987
Max Act: 2.3521. Min Act: -0.1700
Data Index: 314777 (C4 (Web Text))
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.4987. Min Range: -2.4987
Max Act: 2.3521. Min Act: -0.1700
Data Index: 1299814 (C4 (Web Text))
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.4987. Min Range: -2.4987
Max Act: 2.3358. Min Act: -0.1700
Data Index: 1454913 (Python Code)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.4987. Min Range: -2.4987
Max Act: 2.3358. Min Act: -0.1700
Data Index: 1187227 (C4 (Web Text))
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.4987. Min Range: -2.4987
Max Act: 2.3521. Min Act: -0.1700
Data Index: 443767 (C4 (Web Text))
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.4987. Min Range: -2.4987
Max Act: 2.3358. Min Act: -0.1700
Data Index: 532973 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.4987. Min Range: -2.4987
Max Act: 2.3358. Min Act: -0.1700
Data Index: 601920 (C4 (Web Text))
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.4987. Min Range: -2.4987
Max Act: 2.3194. Min Act: -0.1700
Data Index: 635258 (C4 (Web Text))
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.4987. Min Range: -2.4987
Max Act: 2.3194. Min Act: -0.1700
Data Index: 881446 (C4 (Web Text))
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.4987. Min Range: -2.4987
Max Act: 2.3194. Min Act: -0.1700
Data Index: 655584 (C4 (Web Text))
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.4987. Min Range: -2.4987
Max Act: 2.3194. Min Act: -0.1700
Data Index: 598965 (C4 (Web Text))
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.4987. Min Range: -2.4987
Max Act: 2.3194. Min Act: -0.1700
Data Index: 468950 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19