Model: SoLU Model: 6 Layers, 3072 Neurons per Layer
Dataset: The Pile
Neuron 2529 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l-pile')
Text #0
Max Range: 1.5077. Min Range: -1.5077
Max Act: 1.5077. Min Act: -0.0002
Data Index: 1566125 (The Pile)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.5077. Min Range: -1.5077
Max Act: 1.1776. Min Act: -0.0002
Data Index: 719275 (The Pile)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.5077. Min Range: -1.5077
Max Act: 1.0703. Min Act: -0.0002
Data Index: 578884 (The Pile)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.5077. Min Range: -1.5077
Max Act: 1.0556. Min Act: -0.0002
Data Index: 508333 (The Pile)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.5077. Min Range: -1.5077
Max Act: 1.0228. Min Act: -0.0002
Data Index: 694150 (The Pile)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.5077. Min Range: -1.5077
Max Act: 1.0244. Min Act: -0.0002
Data Index: 1852210 (The Pile)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.5077. Min Range: -1.5077
Max Act: 1.0551. Min Act: -0.0002
Data Index: 1364487 (The Pile)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.5077. Min Range: -1.5077
Max Act: 0.9610. Min Act: -0.0002
Data Index: 1208518 (The Pile)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.5077. Min Range: -1.5077
Max Act: 0.9966. Min Act: -0.0002
Data Index: 1994802 (The Pile)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.5077. Min Range: -1.5077
Max Act: 0.9358. Min Act: -0.0002
Data Index: 190475 (The Pile)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.5077. Min Range: -1.5077
Max Act: 0.8873. Min Act: -0.0002
Data Index: 1911074 (The Pile)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.5077. Min Range: -1.5077
Max Act: 0.9254. Min Act: -0.0002
Data Index: 34118 (The Pile)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.5077. Min Range: -1.5077
Max Act: 0.8627. Min Act: -0.0002
Data Index: 198066 (The Pile)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.5077. Min Range: -1.5077
Max Act: 0.9264. Min Act: -0.0002
Data Index: 53190 (The Pile)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.5077. Min Range: -1.5077
Max Act: 0.9368. Min Act: -0.0002
Data Index: 1788579 (The Pile)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.5077. Min Range: -1.5077
Max Act: 0.8748. Min Act: -0.0002
Data Index: 76725 (The Pile)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.5077. Min Range: -1.5077
Max Act: 0.8046. Min Act: -0.0002
Data Index: 425789 (The Pile)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.5077. Min Range: -1.5077
Max Act: 0.8677. Min Act: -0.0002
Data Index: 761797 (The Pile)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.5077. Min Range: -1.5077
Max Act: 0.7935. Min Act: -0.0002
Data Index: 827499 (The Pile)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.5077. Min Range: -1.5077
Max Act: 0.8008. Min Act: -0.0002
Data Index: 419902 (The Pile)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #19