Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: The Pile
Neuron 509 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')
Text #0
Max Range: 1.0704. Min Range: -1.0704
Max Act: 0.9847. Min Act: -0.0001
Data Index: 744836 (The Pile)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.0704. Min Range: -1.0704
Max Act: 0.8860. Min Act: -0.0001
Data Index: 1356006 (The Pile)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.0704. Min Range: -1.0704
Max Act: 0.9851. Min Act: -0.0001
Data Index: 357921 (The Pile)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.0704. Min Range: -1.0704
Max Act: 0.8752. Min Act: -0.0001
Data Index: 56275 (The Pile)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.0704. Min Range: -1.0704
Max Act: 0.8383. Min Act: -0.0001
Data Index: 933118 (The Pile)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.0704. Min Range: -1.0704
Max Act: 1.0704. Min Act: -0.0001
Data Index: 1863681 (The Pile)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.0704. Min Range: -1.0704
Max Act: 0.8981. Min Act: -0.0001
Data Index: 1567699 (The Pile)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.0704. Min Range: -1.0704
Max Act: 0.8114. Min Act: -0.0001
Data Index: 310866 (The Pile)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.0704. Min Range: -1.0704
Max Act: 1.0514. Min Act: -0.0001
Data Index: 684550 (The Pile)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.0704. Min Range: -1.0704
Max Act: 0.8501. Min Act: -0.0001
Data Index: 831871 (The Pile)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.0704. Min Range: -1.0704
Max Act: 0.8610. Min Act: -0.0001
Data Index: 519895 (The Pile)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.0704. Min Range: -1.0704
Max Act: 0.8402. Min Act: -0.0001
Data Index: 706480 (The Pile)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.0704. Min Range: -1.0704
Max Act: 0.6865. Min Act: -0.0001
Data Index: 1650719 (The Pile)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.0704. Min Range: -1.0704
Max Act: 0.6359. Min Act: -0.0001
Data Index: 1798040 (The Pile)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.0704. Min Range: -1.0704
Max Act: 0.9107. Min Act: -0.0001
Data Index: 1035552 (The Pile)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.0704. Min Range: -1.0704
Max Act: 0.7243. Min Act: -0.0001
Data Index: 1143130 (The Pile)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.0704. Min Range: -1.0704
Max Act: 0.8283. Min Act: -0.0001
Data Index: 851300 (The Pile)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.0704. Min Range: -1.0704
Max Act: 0.7803. Min Act: -0.0001
Data Index: 169148 (The Pile)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.0704. Min Range: -1.0704
Max Act: 0.7094. Min Act: -0.0001
Data Index: 715713 (The Pile)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.0704. Min Range: -1.0704
Max Act: 0.9281. Min Act: -0.0001
Data Index: 1763347 (The Pile)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #19