Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2672 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 0.2032. Min Range: -0.2032
Max Act: 0.2032. Min Act: -0.0001
Data Index: 1095731 (C4 (Web Text))
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.2032. Min Range: -0.2032
Max Act: 0.1972. Min Act: -0.0001
Data Index: 675151 (C4 (Web Text))
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.2032. Min Range: -0.2032
Max Act: 0.1840. Min Act: -0.0001
Data Index: 280757 (C4 (Web Text))
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.2032. Min Range: -0.2032
Max Act: 0.1799. Min Act: -0.0001
Data Index: 195919 (C4 (Web Text))
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.2032. Min Range: -0.2032
Max Act: 0.1742. Min Act: -0.0001
Data Index: 997633 (C4 (Web Text))
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.2032. Min Range: -0.2032
Max Act: 0.1683. Min Act: -0.0001
Data Index: 909384 (C4 (Web Text))
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.2032. Min Range: -0.2032
Max Act: 0.1838. Min Act: -0.0001
Data Index: 590172 (C4 (Web Text))
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.2032. Min Range: -0.2032
Max Act: 0.1936. Min Act: -0.0001
Data Index: 20743 (C4 (Web Text))
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.2032. Min Range: -0.2032
Max Act: 0.1793. Min Act: -0.0001
Data Index: 306137 (C4 (Web Text))
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.2032. Min Range: -0.2032
Max Act: 0.1783. Min Act: -0.0001
Data Index: 959589 (C4 (Web Text))
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.2032. Min Range: -0.2032
Max Act: 0.1766. Min Act: -0.0001
Data Index: 49543 (C4 (Web Text))
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.2032. Min Range: -0.2032
Max Act: 0.1695. Min Act: -0.0001
Data Index: 1050430 (C4 (Web Text))
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.2032. Min Range: -0.2032
Max Act: 0.1812. Min Act: -0.0001
Data Index: 1254641 (C4 (Web Text))
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.2032. Min Range: -0.2032
Max Act: 0.1590. Min Act: -0.0001
Data Index: 1110659 (C4 (Web Text))
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.2032. Min Range: -0.2032
Max Act: 0.1741. Min Act: -0.0001
Data Index: 689202 (C4 (Web Text))
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.2032. Min Range: -0.2032
Max Act: 0.1729. Min Act: -0.0001
Data Index: 108066 (C4 (Web Text))
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.2032. Min Range: -0.2032
Max Act: 0.1649. Min Act: -0.0001
Data Index: 311613 (C4 (Web Text))
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.2032. Min Range: -0.2032
Max Act: 0.1543. Min Act: -0.0001
Data Index: 47406 (C4 (Web Text))
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.2032. Min Range: -0.2032
Max Act: 0.1726. Min Act: -0.0001
Data Index: 484652 (C4 (Web Text))
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.2032. Min Range: -0.2032
Max Act: 0.1708. Min Act: -0.0001
Data Index: 1328215 (C4 (Web Text))
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #19