Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: The Pile
Neuron 2098 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')
Text #0
Max Range: 0.2111. Min Range: -0.2111
Max Act: 0.2111. Min Act: -0.0001
Data Index: 1298748 (The Pile)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.2111. Min Range: -0.2111
Max Act: 0.1930. Min Act: -0.0001
Data Index: 1786301 (The Pile)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.2111. Min Range: -0.2111
Max Act: 0.1902. Min Act: -0.0001
Data Index: 1207277 (The Pile)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.2111. Min Range: -0.2111
Max Act: 0.1832. Min Act: -0.0001
Data Index: 334504 (The Pile)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.2111. Min Range: -0.2111
Max Act: 0.1687. Min Act: -0.0001
Data Index: 1166122 (The Pile)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.2111. Min Range: -0.2111
Max Act: 0.1951. Min Act: -0.0001
Data Index: 254827 (The Pile)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.2111. Min Range: -0.2111
Max Act: 0.1857. Min Act: -0.0001
Data Index: 737832 (The Pile)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.2111. Min Range: -0.2111
Max Act: 0.1788. Min Act: -0.0001
Data Index: 503143 (The Pile)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.2111. Min Range: -0.2111
Max Act: 0.1802. Min Act: -0.0001
Data Index: 156834 (The Pile)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.2111. Min Range: -0.2111
Max Act: 0.1825. Min Act: -0.0001
Data Index: 1780945 (The Pile)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.2111. Min Range: -0.2111
Max Act: 0.1896. Min Act: -0.0001
Data Index: 1442897 (The Pile)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.2111. Min Range: -0.2111
Max Act: 0.1786. Min Act: -0.0001
Data Index: 638576 (The Pile)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.2111. Min Range: -0.2111
Max Act: 0.1705. Min Act: -0.0001
Data Index: 1603329 (The Pile)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.2111. Min Range: -0.2111
Max Act: 0.1778. Min Act: -0.0001
Data Index: 1006752 (The Pile)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.2111. Min Range: -0.2111
Max Act: 0.1635. Min Act: -0.0001
Data Index: 1109315 (The Pile)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.2111. Min Range: -0.2111
Max Act: 0.1652. Min Act: -0.0001
Data Index: 1737988 (The Pile)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.2111. Min Range: -0.2111
Max Act: 0.1720. Min Act: -0.0001
Data Index: 456819 (The Pile)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.2111. Min Range: -0.2111
Max Act: 0.1765. Min Act: -0.0001
Data Index: 1952515 (The Pile)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.2111. Min Range: -0.2111
Max Act: 0.1637. Min Act: -0.0001
Data Index: 1576369 (The Pile)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.2111. Min Range: -0.2111
Max Act: 0.1529. Min Act: -0.0001
Data Index: 572863 (The Pile)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #19