Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1122 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 0.1175. Min Range: -0.1175
Max Act: 0.1136. Min Act: -0.0001
Data Index: 325542 (C4 (Web Text))
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.1175. Min Range: -0.1175
Max Act: 0.1077. Min Act: -0.0001
Data Index: 1634243 (Python Code)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.1175. Min Range: -0.1175
Max Act: 0.1118. Min Act: -0.0001
Data Index: 100908 (C4 (Web Text))
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.1175. Min Range: -0.1175
Max Act: 0.1175. Min Act: -0.0001
Data Index: 111819 (C4 (Web Text))
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.1175. Min Range: -0.1175
Max Act: 0.0931. Min Act: -0.0001
Data Index: 1441485 (Python Code)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.1175. Min Range: -0.1175
Max Act: 0.0981. Min Act: -0.0001
Data Index: 1148675 (C4 (Web Text))
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.1175. Min Range: -0.1175
Max Act: 0.0941. Min Act: -0.0001
Data Index: 429062 (C4 (Web Text))
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.1175. Min Range: -0.1175
Max Act: 0.0882. Min Act: -0.0001
Data Index: 1028147 (C4 (Web Text))
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.1175. Min Range: -0.1175
Max Act: 0.0888. Min Act: -0.0001
Data Index: 611302 (C4 (Web Text))
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.1175. Min Range: -0.1175
Max Act: 0.0852. Min Act: -0.0001
Data Index: 477979 (C4 (Web Text))
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.1175. Min Range: -0.1175
Max Act: 0.0845. Min Act: -0.0001
Data Index: 1141642 (C4 (Web Text))
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.1175. Min Range: -0.1175
Max Act: 0.0838. Min Act: -0.0001
Data Index: 748773 (C4 (Web Text))
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.1175. Min Range: -0.1175
Max Act: 0.0904. Min Act: -0.0001
Data Index: 1089420 (C4 (Web Text))
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.1175. Min Range: -0.1175
Max Act: 0.0928. Min Act: -0.0001
Data Index: 1072464 (C4 (Web Text))
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.1175. Min Range: -0.1175
Max Act: 0.0859. Min Act: -0.0001
Data Index: 444898 (C4 (Web Text))
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.1175. Min Range: -0.1175
Max Act: 0.0908. Min Act: -0.0001
Data Index: 161702 (C4 (Web Text))
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.1175. Min Range: -0.1175
Max Act: 0.0851. Min Act: -0.0001
Data Index: 680712 (C4 (Web Text))
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.1175. Min Range: -0.1175
Max Act: 0.0863. Min Act: -0.0001
Data Index: 889962 (C4 (Web Text))
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.1175. Min Range: -0.1175
Max Act: 0.0848. Min Act: -0.0001
Data Index: 165578 (C4 (Web Text))
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.1175. Min Range: -0.1175
Max Act: 0.0848. Min Act: -0.0001
Data Index: 132540 (C4 (Web Text))
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #19