Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: The Pile
Neuron 3479 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')
Text #0
Max Range: 0.0021. Min Range: -0.0021
Max Act: 0.0021. Min Act: -0.0001
Data Index: 1938428 (The Pile)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.0021. Min Range: -0.0021
Max Act: 0.0021. Min Act: -0.0001
Data Index: 845401 (The Pile)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.0021. Min Range: -0.0021
Max Act: 0.0021. Min Act: -0.0001
Data Index: 1224924 (The Pile)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.0021. Min Range: -0.0021
Max Act: 0.0021. Min Act: -0.0001
Data Index: 221188 (The Pile)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.0021. Min Range: -0.0021
Max Act: 0.0021. Min Act: -0.0001
Data Index: 1922847 (The Pile)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.0021. Min Range: -0.0021
Max Act: 0.0020. Min Act: -0.0001
Data Index: 74402 (The Pile)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.0021. Min Range: -0.0021
Max Act: 0.0019. Min Act: -0.0001
Data Index: 800039 (The Pile)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.0021. Min Range: -0.0021
Max Act: 0.0019. Min Act: -0.0001
Data Index: 1574426 (The Pile)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.0021. Min Range: -0.0021
Max Act: 0.0018. Min Act: -0.0001
Data Index: 55304 (The Pile)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.0021. Min Range: -0.0021
Max Act: 0.0018. Min Act: -0.0001
Data Index: 1859466 (The Pile)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.0021. Min Range: -0.0021
Max Act: 0.0017. Min Act: -0.0001
Data Index: 106439 (The Pile)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.0021. Min Range: -0.0021
Max Act: 0.0017. Min Act: -0.0001
Data Index: 1303172 (The Pile)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.0021. Min Range: -0.0021
Max Act: 0.0017. Min Act: -0.0001
Data Index: 187211 (The Pile)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.0021. Min Range: -0.0021
Max Act: 0.0017. Min Act: -0.0001
Data Index: 1597388 (The Pile)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.0021. Min Range: -0.0021
Max Act: 0.0016. Min Act: -0.0001
Data Index: 1459586 (The Pile)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.0021. Min Range: -0.0021
Max Act: 0.0016. Min Act: -0.0001
Data Index: 191312 (The Pile)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.0021. Min Range: -0.0021
Max Act: 0.0016. Min Act: -0.0001
Data Index: 1875135 (The Pile)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.0021. Min Range: -0.0021
Max Act: 0.0016. Min Act: -0.0001
Data Index: 1315376 (The Pile)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.0021. Min Range: -0.0021
Max Act: 0.0016. Min Act: -0.0001
Data Index: 1040955 (The Pile)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.0021. Min Range: -0.0021
Max Act: 0.0015. Min Act: -0.0000
Data Index: 1944137 (The Pile)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #19