Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 4274 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 2.2840. Min Range: -2.2840
Max Act: 2.1368. Min Act: -0.0001
Data Index: 935397 (C4 (Web Text))
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.2840. Min Range: -2.2840
Max Act: 2.2667. Min Act: -0.0001
Data Index: 673358 (C4 (Web Text))
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.2840. Min Range: -2.2840
Max Act: 2.1762. Min Act: -0.0001
Data Index: 539498 (C4 (Web Text))
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.2840. Min Range: -2.2840
Max Act: 2.2840. Min Act: -0.0001
Data Index: 335101 (C4 (Web Text))
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.2840. Min Range: -2.2840
Max Act: 2.1894. Min Act: -0.0001
Data Index: 435620 (C4 (Web Text))
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.2840. Min Range: -2.2840
Max Act: 1.9873. Min Act: -0.0002
Data Index: 951906 (C4 (Web Text))
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.2840. Min Range: -2.2840
Max Act: 1.8129. Min Act: -0.0001
Data Index: 1258424 (C4 (Web Text))
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.2840. Min Range: -2.2840
Max Act: 1.8888. Min Act: -0.0001
Data Index: 591328 (C4 (Web Text))
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.2840. Min Range: -2.2840
Max Act: 1.7985. Min Act: -0.0001
Data Index: 1024125 (C4 (Web Text))
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.2840. Min Range: -2.2840
Max Act: 1.9950. Min Act: -0.0001
Data Index: 153588 (C4 (Web Text))
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.2840. Min Range: -2.2840
Max Act: 2.0909. Min Act: -0.0001
Data Index: 127120 (C4 (Web Text))
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.2840. Min Range: -2.2840
Max Act: 1.8695. Min Act: -0.0002
Data Index: 1066208 (C4 (Web Text))
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.2840. Min Range: -2.2840
Max Act: 1.9269. Min Act: -0.0001
Data Index: 871567 (C4 (Web Text))
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.2840. Min Range: -2.2840
Max Act: 1.8550. Min Act: -0.0001
Data Index: 138139 (C4 (Web Text))
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.2840. Min Range: -2.2840
Max Act: 1.7532. Min Act: -0.0001
Data Index: 126100 (C4 (Web Text))
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.2840. Min Range: -2.2840
Max Act: 1.8971. Min Act: -0.0001
Data Index: 25908 (C4 (Web Text))
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.2840. Min Range: -2.2840
Max Act: 1.8427. Min Act: -0.0002
Data Index: 1333647 (C4 (Web Text))
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.2840. Min Range: -2.2840
Max Act: 1.7243. Min Act: -0.0001
Data Index: 1097587 (C4 (Web Text))
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.2840. Min Range: -2.2840
Max Act: 1.8799. Min Act: -0.0001
Data Index: 670384 (C4 (Web Text))
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.2840. Min Range: -2.2840
Max Act: 1.7316. Min Act: -0.0001
Data Index: 502484 (C4 (Web Text))
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #19