Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: The Pile
Neuron 2123 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')
Text #0
Max Range: 1.7997. Min Range: -1.7997
Max Act: 1.7997. Min Act: -0.0000
Data Index: 1643655 (The Pile)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.7997. Min Range: -1.7997
Max Act: 1.7037. Min Act: -0.0000
Data Index: 1304772 (The Pile)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.7997. Min Range: -1.7997
Max Act: 1.6987. Min Act: -0.0000
Data Index: 684167 (The Pile)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.7997. Min Range: -1.7997
Max Act: 1.7092. Min Act: -0.0000
Data Index: 1883643 (The Pile)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.7997. Min Range: -1.7997
Max Act: 1.7209. Min Act: -0.0000
Data Index: 1597610 (The Pile)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.7997. Min Range: -1.7997
Max Act: 1.6931. Min Act: -0.0000
Data Index: 1706413 (The Pile)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.7997. Min Range: -1.7997
Max Act: 1.7243. Min Act: -0.0000
Data Index: 1785129 (The Pile)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.7997. Min Range: -1.7997
Max Act: 1.7535. Min Act: -0.0000
Data Index: 1678484 (The Pile)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.7997. Min Range: -1.7997
Max Act: 1.7637. Min Act: -0.0000
Data Index: 799474 (The Pile)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.7997. Min Range: -1.7997
Max Act: 1.7054. Min Act: -0.0000
Data Index: 215580 (The Pile)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.7997. Min Range: -1.7997
Max Act: 1.6568. Min Act: -0.0000
Data Index: 1264909 (The Pile)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.7997. Min Range: -1.7997
Max Act: 1.5642. Min Act: -0.0000
Data Index: 31560 (The Pile)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.7997. Min Range: -1.7997
Max Act: 1.6511. Min Act: -0.0000
Data Index: 667185 (The Pile)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.7997. Min Range: -1.7997
Max Act: 1.6048. Min Act: -0.0000
Data Index: 1572756 (The Pile)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.7997. Min Range: -1.7997
Max Act: 1.6214. Min Act: -0.0000
Data Index: 226468 (The Pile)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.7997. Min Range: -1.7997
Max Act: 1.7115. Min Act: -0.0000
Data Index: 1162745 (The Pile)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.7997. Min Range: -1.7997
Max Act: 1.7587. Min Act: -0.0000
Data Index: 146741 (The Pile)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.7997. Min Range: -1.7997
Max Act: 1.6925. Min Act: -0.0000
Data Index: 1028674 (The Pile)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.7997. Min Range: -1.7997
Max Act: 1.6530. Min Act: -0.0000
Data Index: 1638268 (The Pile)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.7997. Min Range: -1.7997
Max Act: 1.6124. Min Act: -0.0000
Data Index: 352015 (The Pile)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #19