Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: The Pile
Neuron 50 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')
Text #0
Max Range: 1.8062. Min Range: -1.8062
Max Act: 1.8062. Min Act: -0.0001
Data Index: 1925189 (The Pile)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.8062. Min Range: -1.8062
Max Act: 1.7797. Min Act: -0.0001
Data Index: 417931 (The Pile)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.8062. Min Range: -1.8062
Max Act: 1.6646. Min Act: -0.0001
Data Index: 71785 (The Pile)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.8062. Min Range: -1.8062
Max Act: 1.6646. Min Act: -0.0001
Data Index: 1499376 (The Pile)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.8062. Min Range: -1.8062
Max Act: 1.6646. Min Act: -0.0001
Data Index: 1478763 (The Pile)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.8062. Min Range: -1.8062
Max Act: 1.6646. Min Act: -0.0001
Data Index: 1204364 (The Pile)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.8062. Min Range: -1.8062
Max Act: 1.6646. Min Act: -0.0001
Data Index: 1392268 (The Pile)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.8062. Min Range: -1.8062
Max Act: 1.6646. Min Act: -0.0001
Data Index: 695387 (The Pile)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.8062. Min Range: -1.8062
Max Act: 1.6646. Min Act: -0.0001
Data Index: 1011218 (The Pile)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.8062. Min Range: -1.8062
Max Act: 1.6646. Min Act: -0.0001
Data Index: 574073 (The Pile)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.8062. Min Range: -1.8062
Max Act: 1.6646. Min Act: -0.0001
Data Index: 676672 (The Pile)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.8062. Min Range: -1.8062
Max Act: 1.6646. Min Act: -0.0001
Data Index: 1295935 (The Pile)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.8062. Min Range: -1.8062
Max Act: 1.6646. Min Act: -0.0001
Data Index: 1095627 (The Pile)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.8062. Min Range: -1.8062
Max Act: 1.6646. Min Act: -0.0001
Data Index: 976295 (The Pile)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.8062. Min Range: -1.8062
Max Act: 1.6646. Min Act: -0.0001
Data Index: 141382 (The Pile)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.8062. Min Range: -1.8062
Max Act: 1.6646. Min Act: -0.0001
Data Index: 1284791 (The Pile)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.8062. Min Range: -1.8062
Max Act: 1.6646. Min Act: -0.0001
Data Index: 52788 (The Pile)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.8062. Min Range: -1.8062
Max Act: 1.6646. Min Act: -0.0001
Data Index: 984521 (The Pile)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.8062. Min Range: -1.8062
Max Act: 1.6646. Min Act: -0.0001
Data Index: 63125 (The Pile)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.8062. Min Range: -1.8062
Max Act: 1.6646. Min Act: -0.0001
Data Index: 193933 (The Pile)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #19