Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 4638 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 4.5029. Min Range: -4.5029
Max Act: 4.5029. Min Act: -0.0001
Data Index: 294348 (C4 (Web Text))
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5029. Min Range: -4.5029
Max Act: 3.9231. Min Act: -0.0000
Data Index: 1617442 (Python Code)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5029. Min Range: -4.5029
Max Act: 3.7487. Min Act: -0.0001
Data Index: 1033537 (C4 (Web Text))
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5029. Min Range: -4.5029
Max Act: 3.3232. Min Act: -0.0001
Data Index: 771508 (C4 (Web Text))
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5029. Min Range: -4.5029
Max Act: 3.5344. Min Act: -0.0001
Data Index: 652360 (C4 (Web Text))
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5029. Min Range: -4.5029
Max Act: 3.0846. Min Act: -0.0001
Data Index: 1223232 (C4 (Web Text))
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5029. Min Range: -4.5029
Max Act: 3.2697. Min Act: -0.0001
Data Index: 1301932 (C4 (Web Text))
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5029. Min Range: -4.5029
Max Act: 2.9859. Min Act: -0.0001
Data Index: 981409 (C4 (Web Text))
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5029. Min Range: -4.5029
Max Act: 3.0926. Min Act: -0.0001
Data Index: 1434 (C4 (Web Text))
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5029. Min Range: -4.5029
Max Act: 3.2381. Min Act: -0.0001
Data Index: 677978 (C4 (Web Text))
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5029. Min Range: -4.5029
Max Act: 3.3710. Min Act: -0.0001
Data Index: 1053376 (C4 (Web Text))
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5029. Min Range: -4.5029
Max Act: 2.9368. Min Act: -0.0001
Data Index: 977805 (C4 (Web Text))
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5029. Min Range: -4.5029
Max Act: 3.0335. Min Act: -0.0001
Data Index: 865665 (C4 (Web Text))
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5029. Min Range: -4.5029
Max Act: 3.0311. Min Act: -0.0001
Data Index: 1285697 (C4 (Web Text))
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5029. Min Range: -4.5029
Max Act: 2.1127. Min Act: -0.0000
Data Index: 1637785 (Python Code)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5029. Min Range: -4.5029
Max Act: 2.8878. Min Act: -0.0001
Data Index: 871018 (C4 (Web Text))
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5029. Min Range: -4.5029
Max Act: 3.0338. Min Act: -0.0001
Data Index: 952891 (C4 (Web Text))
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5029. Min Range: -4.5029
Max Act: 2.7213. Min Act: -0.0001
Data Index: 84913 (C4 (Web Text))
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5029. Min Range: -4.5029
Max Act: 2.7228. Min Act: -0.0001
Data Index: 1112333 (C4 (Web Text))
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5029. Min Range: -4.5029
Max Act: 2.3264. Min Act: -0.0001
Data Index: 520152 (C4 (Web Text))
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #19