Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: The Pile
Neuron 1086 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')
Text #0
Max Range: 1.2386. Min Range: -1.2386
Max Act: 1.1931. Min Act: 0.0000
Data Index: 202248 (The Pile)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.2386. Min Range: -1.2386
Max Act: 1.1572. Min Act: 0.0000
Data Index: 893546 (The Pile)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.2386. Min Range: -1.2386
Max Act: 1.1900. Min Act: -0.0000
Data Index: 746434 (The Pile)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.2386. Min Range: -1.2386
Max Act: 1.2386. Min Act: -0.0000
Data Index: 1102832 (The Pile)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.2386. Min Range: -1.2386
Max Act: 1.1680. Min Act: -0.0000
Data Index: 859012 (The Pile)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.2386. Min Range: -1.2386
Max Act: 1.0828. Min Act: -0.0000
Data Index: 1242737 (The Pile)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.2386. Min Range: -1.2386
Max Act: 1.0901. Min Act: -0.0000
Data Index: 904641 (The Pile)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.2386. Min Range: -1.2386
Max Act: 1.1217. Min Act: 0.0000
Data Index: 522492 (The Pile)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.2386. Min Range: -1.2386
Max Act: 1.0894. Min Act: 0.0000
Data Index: 636303 (The Pile)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.2386. Min Range: -1.2386
Max Act: 1.0270. Min Act: -0.0000
Data Index: 647776 (The Pile)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.2386. Min Range: -1.2386
Max Act: 1.0873. Min Act: -0.0000
Data Index: 745300 (The Pile)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.2386. Min Range: -1.2386
Max Act: 1.0832. Min Act: -0.0000
Data Index: 1264126 (The Pile)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.2386. Min Range: -1.2386
Max Act: 1.0683. Min Act: -0.0000
Data Index: 1093590 (The Pile)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.2386. Min Range: -1.2386
Max Act: 1.0556. Min Act: -0.0000
Data Index: 1419386 (The Pile)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.2386. Min Range: -1.2386
Max Act: 1.1217. Min Act: 0.0000
Data Index: 223099 (The Pile)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.2386. Min Range: -1.2386
Max Act: 1.0363. Min Act: -0.0000
Data Index: 1175415 (The Pile)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.2386. Min Range: -1.2386
Max Act: 1.0215. Min Act: -0.0000
Data Index: 1478108 (The Pile)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.2386. Min Range: -1.2386
Max Act: 1.0107. Min Act: -0.0000
Data Index: 1014689 (The Pile)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.2386. Min Range: -1.2386
Max Act: 1.0050. Min Act: -0.0000
Data Index: 1061410 (The Pile)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.2386. Min Range: -1.2386
Max Act: 0.9358. Min Act: -0.0000
Data Index: 1550304 (The Pile)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #19