Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: The Pile
Neuron 538 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')
Text #0
Max Range: 1.6081. Min Range: -1.6081
Max Act: 1.6081. Min Act: -0.0000
Data Index: 1323569 (The Pile)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.6081. Min Range: -1.6081
Max Act: 1.5100. Min Act: -0.0000
Data Index: 703785 (The Pile)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.6081. Min Range: -1.6081
Max Act: 1.5949. Min Act: -0.0000
Data Index: 1083608 (The Pile)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.6081. Min Range: -1.6081
Max Act: 1.3934. Min Act: -0.0000
Data Index: 328194 (The Pile)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.6081. Min Range: -1.6081
Max Act: 1.4154. Min Act: -0.0000
Data Index: 1732055 (The Pile)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.6081. Min Range: -1.6081
Max Act: 1.0892. Min Act: -0.0000
Data Index: 1743492 (The Pile)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.6081. Min Range: -1.6081
Max Act: 1.1678. Min Act: -0.0000
Data Index: 1933018 (The Pile)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.6081. Min Range: -1.6081
Max Act: 1.1807. Min Act: -0.0000
Data Index: 510806 (The Pile)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.6081. Min Range: -1.6081
Max Act: 1.2087. Min Act: -0.0000
Data Index: 372355 (The Pile)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.6081. Min Range: -1.6081
Max Act: 1.0227. Min Act: -0.0000
Data Index: 1985859 (The Pile)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.6081. Min Range: -1.6081
Max Act: 0.9826. Min Act: -0.0000
Data Index: 900420 (The Pile)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.6081. Min Range: -1.6081
Max Act: 1.0580. Min Act: -0.0000
Data Index: 88843 (The Pile)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.6081. Min Range: -1.6081
Max Act: 1.0180. Min Act: -0.0000
Data Index: 1394646 (The Pile)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.6081. Min Range: -1.6081
Max Act: 0.9695. Min Act: -0.0000
Data Index: 850618 (The Pile)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.6081. Min Range: -1.6081
Max Act: 1.0297. Min Act: -0.0000
Data Index: 687439 (The Pile)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.6081. Min Range: -1.6081
Max Act: 0.8918. Min Act: -0.0000
Data Index: 1287850 (The Pile)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.6081. Min Range: -1.6081
Max Act: 0.9625. Min Act: -0.0000
Data Index: 1598198 (The Pile)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.6081. Min Range: -1.6081
Max Act: 0.9494. Min Act: -0.0000
Data Index: 416642 (The Pile)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.6081. Min Range: -1.6081
Max Act: 0.9539. Min Act: -0.0000
Data Index: 286965 (The Pile)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.6081. Min Range: -1.6081
Max Act: 0.9410. Min Act: -0.0000
Data Index: 1055344 (The Pile)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #19