Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: The Pile
Neuron 4843 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')
Text #0
Max Range: 0.0599. Min Range: -0.0599
Max Act: 0.0599. Min Act: -0.0002
Data Index: 1405495 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.0599. Min Range: -0.0599
Max Act: 0.0599. Min Act: -0.0002
Data Index: 837749 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.0599. Min Range: -0.0599
Max Act: 0.0599. Min Act: -0.0002
Data Index: 1366895 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.0599. Min Range: -0.0599
Max Act: 0.0599. Min Act: -0.0002
Data Index: 677964 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.0599. Min Range: -0.0599
Max Act: 0.0599. Min Act: -0.0002
Data Index: 1693879 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.0599. Min Range: -0.0599
Max Act: 0.0599. Min Act: -0.0002
Data Index: 1046678 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.0599. Min Range: -0.0599
Max Act: 0.0599. Min Act: -0.0002
Data Index: 1062616 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.0599. Min Range: -0.0599
Max Act: 0.0599. Min Act: -0.0002
Data Index: 815154 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.0599. Min Range: -0.0599
Max Act: 0.0565. Min Act: -0.0002
Data Index: 1154915 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.0599. Min Range: -0.0599
Max Act: 0.0565. Min Act: -0.0002
Data Index: 1821587 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.0599. Min Range: -0.0599
Max Act: 0.0565. Min Act: -0.0002
Data Index: 1709569 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.0599. Min Range: -0.0599
Max Act: 0.0565. Min Act: -0.0002
Data Index: 1293947 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.0599. Min Range: -0.0599
Max Act: 0.0565. Min Act: -0.0002
Data Index: 1216566 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.0599. Min Range: -0.0599
Max Act: 0.0565. Min Act: -0.0002
Data Index: 24386 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.0599. Min Range: -0.0599
Max Act: 0.0565. Min Act: -0.0002
Data Index: 67550 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.0599. Min Range: -0.0599
Max Act: 0.0565. Min Act: -0.0002
Data Index: 1382151 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.0599. Min Range: -0.0599
Max Act: 0.0541. Min Act: -0.0002
Data Index: 311211 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.0599. Min Range: -0.0599
Max Act: 0.0541. Min Act: -0.0002
Data Index: 788026 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.0599. Min Range: -0.0599
Max Act: 0.0541. Min Act: -0.0002
Data Index: 746087 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.0599. Min Range: -0.0599
Max Act: 0.0541. Min Act: -0.0002
Data Index: 984099 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #19