Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: The Pile
Neuron 1294 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')
Text #0
Max Range: 0.1130. Min Range: -0.1130
Max Act: 0.1130. Min Act: -0.0001
Data Index: 774302 (The Pile)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.1130. Min Range: -0.1130
Max Act: 0.1118. Min Act: -0.0001
Data Index: 706326 (The Pile)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.1130. Min Range: -0.1130
Max Act: 0.0946. Min Act: -0.0001
Data Index: 174096 (The Pile)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.1130. Min Range: -0.1130
Max Act: 0.0954. Min Act: -0.0001
Data Index: 1848233 (The Pile)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.1130. Min Range: -0.1130
Max Act: 0.1002. Min Act: -0.0001
Data Index: 1524912 (The Pile)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.1130. Min Range: -0.1130
Max Act: 0.1058. Min Act: -0.0001
Data Index: 249656 (The Pile)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.1130. Min Range: -0.1130
Max Act: 0.1051. Min Act: -0.0001
Data Index: 1878818 (The Pile)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.1130. Min Range: -0.1130
Max Act: 0.0967. Min Act: -0.0001
Data Index: 235827 (The Pile)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.1130. Min Range: -0.1130
Max Act: 0.0850. Min Act: -0.0001
Data Index: 253201 (The Pile)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.1130. Min Range: -0.1130
Max Act: 0.0883. Min Act: -0.0001
Data Index: 301053 (The Pile)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.1130. Min Range: -0.1130
Max Act: 0.0877. Min Act: -0.0001
Data Index: 708172 (The Pile)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.1130. Min Range: -0.1130
Max Act: 0.0973. Min Act: -0.0001
Data Index: 1446363 (The Pile)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.1130. Min Range: -0.1130
Max Act: 0.0873. Min Act: -0.0001
Data Index: 836468 (The Pile)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.1130. Min Range: -0.1130
Max Act: 0.1028. Min Act: -0.0001
Data Index: 651504 (The Pile)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.1130. Min Range: -0.1130
Max Act: 0.0873. Min Act: -0.0001
Data Index: 446261 (The Pile)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.1130. Min Range: -0.1130
Max Act: 0.0858. Min Act: -0.0001
Data Index: 1654076 (The Pile)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.1130. Min Range: -0.1130
Max Act: 0.0948. Min Act: -0.0001
Data Index: 1633633 (The Pile)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.1130. Min Range: -0.1130
Max Act: 0.0910. Min Act: -0.0001
Data Index: 1477855 (The Pile)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.1130. Min Range: -0.1130
Max Act: 0.0969. Min Act: -0.0001
Data Index: 3587 (The Pile)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.1130. Min Range: -0.1130
Max Act: 0.0874. Min Act: -0.0001
Data Index: 1516257 (The Pile)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #19