Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: The Pile
Neuron 955 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')
Text #0
Max Range: 0.1679. Min Range: -0.1679
Max Act: 0.1679. Min Act: -0.0002
Data Index: 350644 (The Pile)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.1679. Min Range: -0.1679
Max Act: 0.0995. Min Act: -0.0002
Data Index: 1256771 (The Pile)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.1679. Min Range: -0.1679
Max Act: 0.1065. Min Act: -0.0002
Data Index: 1353351 (The Pile)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.1679. Min Range: -0.1679
Max Act: 0.1141. Min Act: -0.0002
Data Index: 203875 (The Pile)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.1679. Min Range: -0.1679
Max Act: 0.1141. Min Act: -0.0002
Data Index: 1086964 (The Pile)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.1679. Min Range: -0.1679
Max Act: 0.0826. Min Act: -0.0002
Data Index: 36557 (The Pile)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.1679. Min Range: -0.1679
Max Act: 0.0836. Min Act: -0.0001
Data Index: 807524 (The Pile)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.1679. Min Range: -0.1679
Max Act: 0.1232. Min Act: -0.0002
Data Index: 1924827 (The Pile)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.1679. Min Range: -0.1679
Max Act: 0.0554. Min Act: -0.0002
Data Index: 857073 (The Pile)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.1679. Min Range: -0.1679
Max Act: 0.1011. Min Act: -0.0002
Data Index: 787675 (The Pile)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.1679. Min Range: -0.1679
Max Act: 0.0716. Min Act: -0.0002
Data Index: 1930359 (The Pile)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.1679. Min Range: -0.1679
Max Act: 0.0856. Min Act: -0.0002
Data Index: 1911340 (The Pile)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.1679. Min Range: -0.1679
Max Act: 0.0718. Min Act: -0.0002
Data Index: 145906 (The Pile)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.1679. Min Range: -0.1679
Max Act: 0.0735. Min Act: -0.0002
Data Index: 181105 (The Pile)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.1679. Min Range: -0.1679
Max Act: 0.0502. Min Act: -0.0002
Data Index: 1167649 (The Pile)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.1679. Min Range: -0.1679
Max Act: 0.0855. Min Act: -0.0002
Data Index: 1291289 (The Pile)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.1679. Min Range: -0.1679
Max Act: 0.0727. Min Act: -0.0002
Data Index: 1048996 (The Pile)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.1679. Min Range: -0.1679
Max Act: 0.0503. Min Act: -0.0001
Data Index: 192855 (The Pile)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.1679. Min Range: -0.1679
Max Act: 0.0912. Min Act: -0.0002
Data Index: 1412299 (The Pile)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.1679. Min Range: -0.1679
Max Act: 0.0589. Min Act: -0.0002
Data Index: 1058838 (The Pile)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19