Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: The Pile
Neuron 893 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')
Text #0
Max Range: 1.5770. Min Range: -1.5770
Max Act: 1.5770. Min Act: -0.0000
Data Index: 1904739 (The Pile)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.5770. Min Range: -1.5770
Max Act: 1.3115. Min Act: -0.0000
Data Index: 1812765 (The Pile)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.5770. Min Range: -1.5770
Max Act: 1.2426. Min Act: -0.0000
Data Index: 1568516 (The Pile)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.5770. Min Range: -1.5770
Max Act: 1.1424. Min Act: -0.0000
Data Index: 669707 (The Pile)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.5770. Min Range: -1.5770
Max Act: 1.1611. Min Act: -0.0000
Data Index: 73389 (The Pile)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.5770. Min Range: -1.5770
Max Act: 1.1960. Min Act: -0.0000
Data Index: 660795 (The Pile)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.5770. Min Range: -1.5770
Max Act: 1.2158. Min Act: -0.0000
Data Index: 1646504 (The Pile)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.5770. Min Range: -1.5770
Max Act: 1.2211. Min Act: -0.0000
Data Index: 1730807 (The Pile)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.5770. Min Range: -1.5770
Max Act: 1.1982. Min Act: -0.0000
Data Index: 1523122 (The Pile)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.5770. Min Range: -1.5770
Max Act: 1.2115. Min Act: -0.0000
Data Index: 27839 (The Pile)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.5770. Min Range: -1.5770
Max Act: 1.1888. Min Act: -0.0000
Data Index: 425676 (The Pile)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.5770. Min Range: -1.5770
Max Act: 1.1744. Min Act: -0.0000
Data Index: 1777254 (The Pile)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.5770. Min Range: -1.5770
Max Act: 1.2159. Min Act: -0.0000
Data Index: 1518195 (The Pile)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.5770. Min Range: -1.5770
Max Act: 1.1887. Min Act: -0.0000
Data Index: 264001 (The Pile)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.5770. Min Range: -1.5770
Max Act: 1.1412. Min Act: -0.0000
Data Index: 764689 (The Pile)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.5770. Min Range: -1.5770
Max Act: 1.1411. Min Act: -0.0000
Data Index: 1549770 (The Pile)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.5770. Min Range: -1.5770
Max Act: 1.1407. Min Act: -0.0000
Data Index: 1637864 (The Pile)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.5770. Min Range: -1.5770
Max Act: 1.2417. Min Act: -0.0000
Data Index: 434803 (The Pile)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.5770. Min Range: -1.5770
Max Act: 1.1260. Min Act: -0.0000
Data Index: 769815 (The Pile)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.5770. Min Range: -1.5770
Max Act: 1.1665. Min Act: -0.0000
Data Index: 1112533 (The Pile)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #19