Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: The Pile
Neuron 1951 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')
Text #0
Max Range: 1.9323. Min Range: -1.9323
Max Act: 1.8731. Min Act: -0.0000
Data Index: 863581 (The Pile)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.9323. Min Range: -1.9323
Max Act: 1.4044. Min Act: -0.0001
Data Index: 348407 (The Pile)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.9323. Min Range: -1.9323
Max Act: 1.7959. Min Act: -0.0000
Data Index: 1678366 (The Pile)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.9323. Min Range: -1.9323
Max Act: 1.5742. Min Act: -0.0000
Data Index: 111874 (The Pile)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.9323. Min Range: -1.9323
Max Act: 1.9323. Min Act: -0.0000
Data Index: 118382 (The Pile)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.9323. Min Range: -1.9323
Max Act: 1.6329. Min Act: -0.0000
Data Index: 1736697 (The Pile)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.9323. Min Range: -1.9323
Max Act: 1.7817. Min Act: -0.0000
Data Index: 699011 (The Pile)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.9323. Min Range: -1.9323
Max Act: 1.8414. Min Act: -0.0001
Data Index: 1091817 (The Pile)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.9323. Min Range: -1.9323
Max Act: 1.7627. Min Act: -0.0000
Data Index: 16821 (The Pile)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.9323. Min Range: -1.9323
Max Act: 1.6475. Min Act: -0.0000
Data Index: 1406850 (The Pile)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.9323. Min Range: -1.9323
Max Act: 1.4351. Min Act: -0.0000
Data Index: 232268 (The Pile)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.9323. Min Range: -1.9323
Max Act: 1.5809. Min Act: -0.0000
Data Index: 1668927 (The Pile)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.9323. Min Range: -1.9323
Max Act: 1.6236. Min Act: -0.0000
Data Index: 105192 (The Pile)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.9323. Min Range: -1.9323
Max Act: 1.5802. Min Act: -0.0000
Data Index: 609738 (The Pile)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.9323. Min Range: -1.9323
Max Act: 1.3532. Min Act: -0.0000
Data Index: 1702041 (The Pile)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.9323. Min Range: -1.9323
Max Act: 1.5773. Min Act: -0.0000
Data Index: 680967 (The Pile)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.9323. Min Range: -1.9323
Max Act: 1.4840. Min Act: -0.0000
Data Index: 30521 (The Pile)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.9323. Min Range: -1.9323
Max Act: 1.4891. Min Act: -0.0000
Data Index: 1562007 (The Pile)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.9323. Min Range: -1.9323
Max Act: 1.5613. Min Act: -0.0000
Data Index: 1548056 (The Pile)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.9323. Min Range: -1.9323
Max Act: 1.4863. Min Act: -0.0000
Data Index: 1872833 (The Pile)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #19