Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: The Pile
Neuron 1852 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')
Text #0
Max Range: 1.1894. Min Range: -1.1894
Max Act: 1.1894. Min Act: -0.0001
Data Index: 239080 (The Pile)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.1894. Min Range: -1.1894
Max Act: 1.1179. Min Act: -0.0001
Data Index: 464708 (The Pile)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.1894. Min Range: -1.1894
Max Act: 1.0770. Min Act: -0.0001
Data Index: 188643 (The Pile)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.1894. Min Range: -1.1894
Max Act: 1.1111. Min Act: -0.0001
Data Index: 537516 (The Pile)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.1894. Min Range: -1.1894
Max Act: 1.0576. Min Act: -0.0001
Data Index: 547523 (The Pile)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.1894. Min Range: -1.1894
Max Act: 1.0348. Min Act: -0.0001
Data Index: 1577112 (The Pile)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.1894. Min Range: -1.1894
Max Act: 1.0091. Min Act: -0.0001
Data Index: 625231 (The Pile)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.1894. Min Range: -1.1894
Max Act: 0.9732. Min Act: -0.0001
Data Index: 1452447 (The Pile)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.1894. Min Range: -1.1894
Max Act: 1.0166. Min Act: -0.0001
Data Index: 114356 (The Pile)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.1894. Min Range: -1.1894
Max Act: 1.0155. Min Act: -0.0001
Data Index: 437894 (The Pile)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.1894. Min Range: -1.1894
Max Act: 0.9582. Min Act: -0.0001
Data Index: 228559 (The Pile)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.1894. Min Range: -1.1894
Max Act: 0.9523. Min Act: -0.0000
Data Index: 596516 (The Pile)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.1894. Min Range: -1.1894
Max Act: 0.9430. Min Act: -0.0001
Data Index: 836163 (The Pile)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.1894. Min Range: -1.1894
Max Act: 0.9700. Min Act: -0.0001
Data Index: 326835 (The Pile)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.1894. Min Range: -1.1894
Max Act: 0.9517. Min Act: -0.0001
Data Index: 1369904 (The Pile)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.1894. Min Range: -1.1894
Max Act: 0.8988. Min Act: -0.0001
Data Index: 914467 (The Pile)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.1894. Min Range: -1.1894
Max Act: 0.9691. Min Act: -0.0001
Data Index: 66629 (The Pile)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.1894. Min Range: -1.1894
Max Act: 0.8585. Min Act: -0.0001
Data Index: 1411423 (The Pile)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.1894. Min Range: -1.1894
Max Act: 0.8365. Min Act: -0.0001
Data Index: 463970 (The Pile)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.1894. Min Range: -1.1894
Max Act: 0.8346. Min Act: -0.0001
Data Index: 109788 (The Pile)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #19