Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2987 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 6.8035. Min Range: -6.8035
Max Act: 6.8035. Min Act: -0.0001
Data Index: 393857 (C4 (Web Text))
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8035. Min Range: -6.8035
Max Act: 6.0366. Min Act: -0.0001
Data Index: 479663 (C4 (Web Text))
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8035. Min Range: -6.8035
Max Act: 5.6214. Min Act: -0.0001
Data Index: 468898 (C4 (Web Text))
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8035. Min Range: -6.8035
Max Act: 5.7098. Min Act: -0.0001
Data Index: 1104778 (C4 (Web Text))
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8035. Min Range: -6.8035
Max Act: 5.0536. Min Act: -0.0001
Data Index: 629214 (C4 (Web Text))
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8035. Min Range: -6.8035
Max Act: 5.0338. Min Act: -0.0001
Data Index: 780065 (C4 (Web Text))
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8035. Min Range: -6.8035
Max Act: 5.1668. Min Act: -0.0001
Data Index: 828220 (C4 (Web Text))
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8035. Min Range: -6.8035
Max Act: 5.0523. Min Act: -0.0001
Data Index: 428352 (C4 (Web Text))
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8035. Min Range: -6.8035
Max Act: 4.8560. Min Act: -0.0001
Data Index: 528989 (C4 (Web Text))
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8035. Min Range: -6.8035
Max Act: 4.8834. Min Act: -0.0001
Data Index: 908558 (C4 (Web Text))
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8035. Min Range: -6.8035
Max Act: 4.6485. Min Act: -0.0001
Data Index: 1012010 (C4 (Web Text))
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8035. Min Range: -6.8035
Max Act: 4.6716. Min Act: -0.0001
Data Index: 336476 (C4 (Web Text))
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8035. Min Range: -6.8035
Max Act: 4.2194. Min Act: -0.0001
Data Index: 752841 (C4 (Web Text))
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8035. Min Range: -6.8035
Max Act: 4.6640. Min Act: -0.0001
Data Index: 640333 (C4 (Web Text))
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8035. Min Range: -6.8035
Max Act: 4.5990. Min Act: -0.0001
Data Index: 1179881 (C4 (Web Text))
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8035. Min Range: -6.8035
Max Act: 4.3449. Min Act: -0.0001
Data Index: 477159 (C4 (Web Text))
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8035. Min Range: -6.8035
Max Act: 4.3611. Min Act: -0.0001
Data Index: 962964 (C4 (Web Text))
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8035. Min Range: -6.8035
Max Act: 4.4934. Min Act: -0.0001
Data Index: 527880 (C4 (Web Text))
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8035. Min Range: -6.8035
Max Act: 4.9776. Min Act: -0.0001
Data Index: 699353 (C4 (Web Text))
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8035. Min Range: -6.8035
Max Act: 4.5844. Min Act: -0.0001
Data Index: 1070828 (C4 (Web Text))
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #19