Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: The Pile
Neuron 2372 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')
Text #0
Max Range: 3.5011. Min Range: -3.5011
Max Act: 3.5011. Min Act: -0.0000
Data Index: 1914144 (The Pile)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5011. Min Range: -3.5011
Max Act: 3.4767. Min Act: -0.0000
Data Index: 519333 (The Pile)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5011. Min Range: -3.5011
Max Act: 3.3126. Min Act: -0.0000
Data Index: 582901 (The Pile)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5011. Min Range: -3.5011
Max Act: 3.3172. Min Act: -0.0000
Data Index: 1039459 (The Pile)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5011. Min Range: -3.5011
Max Act: 2.9335. Min Act: -0.0000
Data Index: 1584964 (The Pile)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5011. Min Range: -3.5011
Max Act: 3.1674. Min Act: -0.0000
Data Index: 1652825 (The Pile)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5011. Min Range: -3.5011
Max Act: 3.1618. Min Act: -0.0000
Data Index: 15442 (The Pile)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5011. Min Range: -3.5011
Max Act: 2.9853. Min Act: -0.0000
Data Index: 1873664 (The Pile)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5011. Min Range: -3.5011
Max Act: 3.1298. Min Act: -0.0000
Data Index: 903771 (The Pile)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5011. Min Range: -3.5011
Max Act: 3.2075. Min Act: -0.0000
Data Index: 1152812 (The Pile)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5011. Min Range: -3.5011
Max Act: 2.9132. Min Act: -0.0000
Data Index: 1339201 (The Pile)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5011. Min Range: -3.5011
Max Act: 3.0423. Min Act: -0.0000
Data Index: 1692060 (The Pile)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5011. Min Range: -3.5011
Max Act: 3.0550. Min Act: -0.0000
Data Index: 1164068 (The Pile)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5011. Min Range: -3.5011
Max Act: 3.0156. Min Act: -0.0000
Data Index: 906288 (The Pile)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5011. Min Range: -3.5011
Max Act: 2.9907. Min Act: -0.0000
Data Index: 553930 (The Pile)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5011. Min Range: -3.5011
Max Act: 2.8626. Min Act: -0.0000
Data Index: 1237605 (The Pile)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5011. Min Range: -3.5011
Max Act: 2.8662. Min Act: -0.0000
Data Index: 1859458 (The Pile)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5011. Min Range: -3.5011
Max Act: 2.8776. Min Act: -0.0000
Data Index: 484248 (The Pile)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5011. Min Range: -3.5011
Max Act: 2.8796. Min Act: -0.0000
Data Index: 1953779 (The Pile)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5011. Min Range: -3.5011
Max Act: 2.8670. Min Act: -0.0000
Data Index: 1126330 (The Pile)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #19