Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 4254 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 2.1713. Min Range: -2.1713
Max Act: 2.0802. Min Act: -0.0001
Data Index: 136318 (C4 (Web Text))
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.1713. Min Range: -2.1713
Max Act: 2.1713. Min Act: -0.0001
Data Index: 31263 (C4 (Web Text))
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.1713. Min Range: -2.1713
Max Act: 2.0073. Min Act: -0.0001
Data Index: 128635 (C4 (Web Text))
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.1713. Min Range: -2.1713
Max Act: 2.0633. Min Act: -0.0001
Data Index: 247438 (C4 (Web Text))
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.1713. Min Range: -2.1713
Max Act: 2.0160. Min Act: -0.0001
Data Index: 333083 (C4 (Web Text))
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.1713. Min Range: -2.1713
Max Act: 2.0665. Min Act: -0.0001
Data Index: 398974 (C4 (Web Text))
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.1713. Min Range: -2.1713
Max Act: 1.9830. Min Act: -0.0001
Data Index: 1314801 (C4 (Web Text))
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.1713. Min Range: -2.1713
Max Act: 1.9035. Min Act: -0.0001
Data Index: 769723 (C4 (Web Text))
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.1713. Min Range: -2.1713
Max Act: 1.9516. Min Act: -0.0001
Data Index: 587893 (C4 (Web Text))
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.1713. Min Range: -2.1713
Max Act: 1.8860. Min Act: -0.0001
Data Index: 178485 (C4 (Web Text))
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.1713. Min Range: -2.1713
Max Act: 2.0644. Min Act: -0.0001
Data Index: 317945 (C4 (Web Text))
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.1713. Min Range: -2.1713
Max Act: 2.0102. Min Act: -0.0001
Data Index: 184954 (C4 (Web Text))
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.1713. Min Range: -2.1713
Max Act: 1.9660. Min Act: -0.0001
Data Index: 1014070 (C4 (Web Text))
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.1713. Min Range: -2.1713
Max Act: 1.8767. Min Act: -0.0001
Data Index: 897213 (C4 (Web Text))
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.1713. Min Range: -2.1713
Max Act: 1.9175. Min Act: -0.0001
Data Index: 189863 (C4 (Web Text))
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.1713. Min Range: -2.1713
Max Act: 2.0642. Min Act: -0.0001
Data Index: 14191 (C4 (Web Text))
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.1713. Min Range: -2.1713
Max Act: 2.0208. Min Act: -0.0001
Data Index: 806380 (C4 (Web Text))
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.1713. Min Range: -2.1713
Max Act: 1.9022. Min Act: -0.0001
Data Index: 992971 (C4 (Web Text))
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.1713. Min Range: -2.1713
Max Act: 1.7911. Min Act: -0.0001
Data Index: 178514 (C4 (Web Text))
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.1713. Min Range: -2.1713
Max Act: 2.0448. Min Act: -0.0001
Data Index: 881828 (C4 (Web Text))
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #19