Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: The Pile
Neuron 2461 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')
Text #0
Max Range: 1.9068. Min Range: -1.9068
Max Act: 1.9068. Min Act: -0.0000
Data Index: 235172 (The Pile)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.9068. Min Range: -1.9068
Max Act: 1.7045. Min Act: -0.0000
Data Index: 8484 (The Pile)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.9068. Min Range: -1.9068
Max Act: 1.8868. Min Act: -0.0000
Data Index: 56294 (The Pile)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.9068. Min Range: -1.9068
Max Act: 1.5892. Min Act: 0.0000
Data Index: 780013 (The Pile)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.9068. Min Range: -1.9068
Max Act: 1.6125. Min Act: -0.0000
Data Index: 48943 (The Pile)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.9068. Min Range: -1.9068
Max Act: 1.6478. Min Act: -0.0000
Data Index: 1302080 (The Pile)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.9068. Min Range: -1.9068
Max Act: 1.5410. Min Act: 0.0001
Data Index: 1651521 (The Pile)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.9068. Min Range: -1.9068
Max Act: 1.6397. Min Act: -0.0000
Data Index: 1548429 (The Pile)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.9068. Min Range: -1.9068
Max Act: 1.5486. Min Act: -0.0000
Data Index: 1971501 (The Pile)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.9068. Min Range: -1.9068
Max Act: 1.4365. Min Act: -0.0000
Data Index: 558956 (The Pile)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.9068. Min Range: -1.9068
Max Act: 1.4353. Min Act: -0.0000
Data Index: 1710582 (The Pile)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.9068. Min Range: -1.9068
Max Act: 1.5032. Min Act: 0.0001
Data Index: 4322 (The Pile)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.9068. Min Range: -1.9068
Max Act: 1.4850. Min Act: 0.0000
Data Index: 246030 (The Pile)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.9068. Min Range: -1.9068
Max Act: 1.5394. Min Act: -0.0000
Data Index: 1414812 (The Pile)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.9068. Min Range: -1.9068
Max Act: 1.3771. Min Act: -0.0000
Data Index: 137488 (The Pile)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.9068. Min Range: -1.9068
Max Act: 1.2598. Min Act: -0.0000
Data Index: 1245701 (The Pile)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.9068. Min Range: -1.9068
Max Act: 1.3348. Min Act: -0.0000
Data Index: 490268 (The Pile)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.9068. Min Range: -1.9068
Max Act: 1.4153. Min Act: 0.0000
Data Index: 582923 (The Pile)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.9068. Min Range: -1.9068
Max Act: 1.3998. Min Act: -0.0000
Data Index: 1444744 (The Pile)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.9068. Min Range: -1.9068
Max Act: 1.3311. Min Act: 0.0000
Data Index: 378503 (The Pile)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #19