Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: The Pile
Neuron 1819 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')
Text #0
Max Range: 0.2356. Min Range: -0.2356
Max Act: 0.2356. Min Act: -0.0001
Data Index: 425836 (The Pile)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.2356. Min Range: -0.2356
Max Act: 0.1990. Min Act: -0.0001
Data Index: 824725 (The Pile)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.2356. Min Range: -0.2356
Max Act: 0.2041. Min Act: -0.0001
Data Index: 23577 (The Pile)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.2356. Min Range: -0.2356
Max Act: 0.1880. Min Act: -0.0001
Data Index: 739392 (The Pile)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.2356. Min Range: -0.2356
Max Act: 0.1833. Min Act: -0.0001
Data Index: 1842382 (The Pile)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.2356. Min Range: -0.2356
Max Act: 0.1875. Min Act: -0.0001
Data Index: 1106847 (The Pile)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.2356. Min Range: -0.2356
Max Act: 0.1880. Min Act: -0.0001
Data Index: 1466124 (The Pile)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.2356. Min Range: -0.2356
Max Act: 0.1918. Min Act: -0.0001
Data Index: 937397 (The Pile)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.2356. Min Range: -0.2356
Max Act: 0.1734. Min Act: -0.0001
Data Index: 621577 (The Pile)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.2356. Min Range: -0.2356
Max Act: 0.1627. Min Act: -0.0001
Data Index: 406826 (The Pile)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.2356. Min Range: -0.2356
Max Act: 0.1724. Min Act: -0.0001
Data Index: 1075487 (The Pile)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.2356. Min Range: -0.2356
Max Act: 0.1880. Min Act: -0.0001
Data Index: 1220325 (The Pile)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.2356. Min Range: -0.2356
Max Act: 0.1757. Min Act: -0.0001
Data Index: 1135970 (The Pile)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.2356. Min Range: -0.2356
Max Act: 0.1773. Min Act: -0.0001
Data Index: 1601276 (The Pile)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.2356. Min Range: -0.2356
Max Act: 0.1691. Min Act: -0.0001
Data Index: 199207 (The Pile)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.2356. Min Range: -0.2356
Max Act: 0.1749. Min Act: -0.0001
Data Index: 629678 (The Pile)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.2356. Min Range: -0.2356
Max Act: 0.1604. Min Act: -0.0001
Data Index: 946891 (The Pile)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.2356. Min Range: -0.2356
Max Act: 0.1423. Min Act: -0.0001
Data Index: 16454 (The Pile)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.2356. Min Range: -0.2356
Max Act: 0.1714. Min Act: -0.0001
Data Index: 1333517 (The Pile)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.2356. Min Range: -0.2356
Max Act: 0.1480. Min Act: -0.0001
Data Index: 1354098 (The Pile)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #19