Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: The Pile
Neuron 3114 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')
Text #0
Max Range: 1.7217. Min Range: -1.7217
Max Act: 1.7217. Min Act: -0.0000
Data Index: 1136741 (The Pile)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.7217. Min Range: -1.7217
Max Act: 1.6851. Min Act: -0.0000
Data Index: 1838630 (The Pile)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.7217. Min Range: -1.7217
Max Act: 1.5875. Min Act: -0.0000
Data Index: 1772500 (The Pile)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.7217. Min Range: -1.7217
Max Act: 1.5826. Min Act: -0.0000
Data Index: 1743448 (The Pile)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.7217. Min Range: -1.7217
Max Act: 1.5642. Min Act: -0.0000
Data Index: 179966 (The Pile)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.7217. Min Range: -1.7217
Max Act: 1.4953. Min Act: -0.0000
Data Index: 51934 (The Pile)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.7217. Min Range: -1.7217
Max Act: 1.4038. Min Act: -0.0000
Data Index: 1751414 (The Pile)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.7217. Min Range: -1.7217
Max Act: 1.4026. Min Act: -0.0000
Data Index: 895791 (The Pile)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.7217. Min Range: -1.7217
Max Act: 1.4278. Min Act: -0.0000
Data Index: 311591 (The Pile)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.7217. Min Range: -1.7217
Max Act: 1.3842. Min Act: -0.0000
Data Index: 482295 (The Pile)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.7217. Min Range: -1.7217
Max Act: 1.3923. Min Act: -0.0000
Data Index: 1232550 (The Pile)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.7217. Min Range: -1.7217
Max Act: 1.3676. Min Act: -0.0000
Data Index: 890688 (The Pile)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.7217. Min Range: -1.7217
Max Act: 1.2937. Min Act: -0.0000
Data Index: 724268 (The Pile)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.7217. Min Range: -1.7217
Max Act: 1.4005. Min Act: -0.0000
Data Index: 745954 (The Pile)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.7217. Min Range: -1.7217
Max Act: 1.3569. Min Act: -0.0000
Data Index: 1061671 (The Pile)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.7217. Min Range: -1.7217
Max Act: 1.3576. Min Act: -0.0000
Data Index: 88526 (The Pile)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.7217. Min Range: -1.7217
Max Act: 1.3133. Min Act: -0.0000
Data Index: 338004 (The Pile)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.7217. Min Range: -1.7217
Max Act: 1.2627. Min Act: -0.0000
Data Index: 381230 (The Pile)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.7217. Min Range: -1.7217
Max Act: 1.3293. Min Act: -0.0000
Data Index: 566107 (The Pile)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.7217. Min Range: -1.7217
Max Act: 1.3303. Min Act: -0.0000
Data Index: 939264 (The Pile)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #19