Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 951 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 0.2013. Min Range: -0.2013
Max Act: 0.2013. Min Act: -0.0001
Data Index: 1048386 (C4 (Web Text))
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.2013. Min Range: -0.2013
Max Act: 0.1910. Min Act: -0.0001
Data Index: 268967 (C4 (Web Text))
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.2013. Min Range: -0.2013
Max Act: 0.1725. Min Act: -0.0000
Data Index: 193903 (C4 (Web Text))
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.2013. Min Range: -0.2013
Max Act: 0.1783. Min Act: -0.0001
Data Index: 1099860 (C4 (Web Text))
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.2013. Min Range: -0.2013
Max Act: 0.1808. Min Act: -0.0001
Data Index: 128570 (C4 (Web Text))
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.2013. Min Range: -0.2013
Max Act: 0.1785. Min Act: -0.0001
Data Index: 593419 (C4 (Web Text))
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.2013. Min Range: -0.2013
Max Act: 0.1802. Min Act: -0.0001
Data Index: 835584 (C4 (Web Text))
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.2013. Min Range: -0.2013
Max Act: 0.1852. Min Act: 0.0000
Data Index: 456682 (C4 (Web Text))
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.2013. Min Range: -0.2013
Max Act: 0.1876. Min Act: -0.0001
Data Index: 674956 (C4 (Web Text))
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.2013. Min Range: -0.2013
Max Act: 0.1687. Min Act: -0.0001
Data Index: 210505 (C4 (Web Text))
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.2013. Min Range: -0.2013
Max Act: 0.1678. Min Act: 0.0000
Data Index: 1155171 (C4 (Web Text))
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.2013. Min Range: -0.2013
Max Act: 0.1753. Min Act: -0.0001
Data Index: 737971 (C4 (Web Text))
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.2013. Min Range: -0.2013
Max Act: 0.1635. Min Act: -0.0001
Data Index: 1224009 (C4 (Web Text))
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.2013. Min Range: -0.2013
Max Act: 0.1251. Min Act: -0.0001
Data Index: 1429196 (Python Code)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.2013. Min Range: -0.2013
Max Act: 0.1595. Min Act: -0.0000
Data Index: 956994 (C4 (Web Text))
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.2013. Min Range: -0.2013
Max Act: 0.1573. Min Act: -0.0000
Data Index: 119026 (C4 (Web Text))
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.2013. Min Range: -0.2013
Max Act: 0.1574. Min Act: -0.0001
Data Index: 175197 (C4 (Web Text))
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.2013. Min Range: -0.2013
Max Act: 0.1514. Min Act: -0.0000
Data Index: 1637785 (Python Code)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.2013. Min Range: -0.2013
Max Act: 0.1561. Min Act: 0.0000
Data Index: 808316 (C4 (Web Text))
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.2013. Min Range: -0.2013
Max Act: 0.1631. Min Act: -0.0000
Data Index: 812135 (C4 (Web Text))
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #19