Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: The Pile
Neuron 3039 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')
Text #0
Max Range: 1.1836. Min Range: -1.1836
Max Act: 1.1836. Min Act: -0.0001
Data Index: 1053110 (The Pile)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.1836. Min Range: -1.1836
Max Act: 1.1595. Min Act: -0.0001
Data Index: 1902179 (The Pile)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.1836. Min Range: -1.1836
Max Act: 1.0279. Min Act: -0.0001
Data Index: 1467430 (The Pile)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.1836. Min Range: -1.1836
Max Act: 1.1530. Min Act: -0.0001
Data Index: 1900897 (The Pile)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.1836. Min Range: -1.1836
Max Act: 1.0480. Min Act: -0.0001
Data Index: 222950 (The Pile)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.1836. Min Range: -1.1836
Max Act: 1.1411. Min Act: -0.0001
Data Index: 678366 (The Pile)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.1836. Min Range: -1.1836
Max Act: 1.0991. Min Act: -0.0001
Data Index: 1889948 (The Pile)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.1836. Min Range: -1.1836
Max Act: 1.1251. Min Act: -0.0001
Data Index: 1453908 (The Pile)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.1836. Min Range: -1.1836
Max Act: 1.0626. Min Act: -0.0001
Data Index: 260956 (The Pile)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.1836. Min Range: -1.1836
Max Act: 1.0809. Min Act: -0.0001
Data Index: 334583 (The Pile)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.1836. Min Range: -1.1836
Max Act: 1.0809. Min Act: -0.0001
Data Index: 24563 (The Pile)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.1836. Min Range: -1.1836
Max Act: 1.1756. Min Act: -0.0001
Data Index: 1678353 (The Pile)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.1836. Min Range: -1.1836
Max Act: 1.1057. Min Act: -0.0001
Data Index: 287314 (The Pile)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.1836. Min Range: -1.1836
Max Act: 1.1684. Min Act: -0.0001
Data Index: 766944 (The Pile)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.1836. Min Range: -1.1836
Max Act: 1.0034. Min Act: -0.0001
Data Index: 767788 (The Pile)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.1836. Min Range: -1.1836
Max Act: 1.0145. Min Act: -0.0001
Data Index: 1797148 (The Pile)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.1836. Min Range: -1.1836
Max Act: 1.0942. Min Act: -0.0001
Data Index: 1510041 (The Pile)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.1836. Min Range: -1.1836
Max Act: 1.1037. Min Act: -0.0001
Data Index: 611512 (The Pile)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.1836. Min Range: -1.1836
Max Act: 1.0709. Min Act: -0.0001
Data Index: 135426 (The Pile)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.1836. Min Range: -1.1836
Max Act: 1.1373. Min Act: -0.0001
Data Index: 513346 (The Pile)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #19