Model: SoLU Model: 4 Layers, 2048 Neurons per Layer
Dataset: The Pile
Neuron 2040 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l-pile')
Text #0
Max Range: 0.0007. Min Range: -0.0007
Max Act: 0.0007. Min Act: -0.0003
Data Index: 221024 (The Pile)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.0007. Min Range: -0.0007
Max Act: 0.0006. Min Act: -0.0003
Data Index: 524135 (The Pile)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.0007. Min Range: -0.0007
Max Act: 0.0005. Min Act: -0.0003
Data Index: 1308249 (The Pile)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.0007. Min Range: -0.0007
Max Act: 0.0005. Min Act: -0.0003
Data Index: 925387 (The Pile)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.0007. Min Range: -0.0007
Max Act: 0.0005. Min Act: -0.0002
Data Index: 1464535 (The Pile)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.0007. Min Range: -0.0007
Max Act: 0.0005. Min Act: -0.0003
Data Index: 1244045 (The Pile)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.0007. Min Range: -0.0007
Max Act: 0.0005. Min Act: -0.0003
Data Index: 606089 (The Pile)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.0007. Min Range: -0.0007
Max Act: 0.0004. Min Act: -0.0003
Data Index: 1418426 (The Pile)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.0007. Min Range: -0.0007
Max Act: 0.0004. Min Act: -0.0003
Data Index: 1255450 (The Pile)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.0007. Min Range: -0.0007
Max Act: 0.0005. Min Act: -0.0003
Data Index: 1507554 (The Pile)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.0007. Min Range: -0.0007
Max Act: 0.0004. Min Act: -0.0003
Data Index: 631307 (The Pile)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.0007. Min Range: -0.0007
Max Act: 0.0004. Min Act: -0.0003
Data Index: 1060875 (The Pile)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.0007. Min Range: -0.0007
Max Act: 0.0004. Min Act: -0.0003
Data Index: 32075 (The Pile)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.0007. Min Range: -0.0007
Max Act: 0.0004. Min Act: -0.0003
Data Index: 1262539 (The Pile)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.0007. Min Range: -0.0007
Max Act: 0.0004. Min Act: -0.0003
Data Index: 51345 (The Pile)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.0007. Min Range: -0.0007
Max Act: 0.0004. Min Act: -0.0003
Data Index: 1616131 (The Pile)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.0007. Min Range: -0.0007
Max Act: 0.0004. Min Act: -0.0003
Data Index: 1423136 (The Pile)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.0007. Min Range: -0.0007
Max Act: 0.0004. Min Act: -0.0003
Data Index: 1965400 (The Pile)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.0007. Min Range: -0.0007
Max Act: 0.0004. Min Act: -0.0003
Data Index: 132136 (The Pile)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.0007. Min Range: -0.0007
Max Act: 0.0004. Min Act: -0.0003
Data Index: 1476342 (The Pile)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19