Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: The Pile
Neuron 3454 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')
Text #0
Max Range: 0.7527. Min Range: -0.7527
Max Act: 0.7527. Min Act: -0.0001
Data Index: 1806468 (The Pile)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.7527. Min Range: -0.7527
Max Act: 0.7376. Min Act: -0.0001
Data Index: 914633 (The Pile)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.7527. Min Range: -0.7527
Max Act: 0.7189. Min Act: -0.0001
Data Index: 743969 (The Pile)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.7527. Min Range: -0.7527
Max Act: 0.6955. Min Act: -0.0001
Data Index: 1244391 (The Pile)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.7527. Min Range: -0.7527
Max Act: 0.7023. Min Act: -0.0001
Data Index: 536557 (The Pile)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.7527. Min Range: -0.7527
Max Act: 0.6961. Min Act: -0.0001
Data Index: 1921892 (The Pile)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.7527. Min Range: -0.7527
Max Act: 0.7310. Min Act: -0.0001
Data Index: 1459271 (The Pile)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.7527. Min Range: -0.7527
Max Act: 0.6573. Min Act: -0.0001
Data Index: 1271256 (The Pile)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.7527. Min Range: -0.7527
Max Act: 0.6784. Min Act: -0.0001
Data Index: 1479660 (The Pile)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.7527. Min Range: -0.7527
Max Act: 0.6783. Min Act: -0.0001
Data Index: 1791174 (The Pile)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.7527. Min Range: -0.7527
Max Act: 0.6703. Min Act: -0.0001
Data Index: 333660 (The Pile)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.7527. Min Range: -0.7527
Max Act: 0.6810. Min Act: -0.0001
Data Index: 986784 (The Pile)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.7527. Min Range: -0.7527
Max Act: 0.6249. Min Act: -0.0001
Data Index: 1280989 (The Pile)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.7527. Min Range: -0.7527
Max Act: 0.6838. Min Act: -0.0001
Data Index: 228452 (The Pile)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.7527. Min Range: -0.7527
Max Act: 0.6646. Min Act: -0.0001
Data Index: 637797 (The Pile)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.7527. Min Range: -0.7527
Max Act: 0.6616. Min Act: -0.0001
Data Index: 1888155 (The Pile)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.7527. Min Range: -0.7527
Max Act: 0.6694. Min Act: -0.0001
Data Index: 1815700 (The Pile)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.7527. Min Range: -0.7527
Max Act: 0.6032. Min Act: -0.0001
Data Index: 1230735 (The Pile)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.7527. Min Range: -0.7527
Max Act: 0.6306. Min Act: -0.0001
Data Index: 1045771 (The Pile)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.7527. Min Range: -0.7527
Max Act: 0.6119. Min Act: -0.0001
Data Index: 720894 (The Pile)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #19