Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3934 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 0.8327. Min Range: -0.8327
Max Act: 0.7887. Min Act: -0.0001
Data Index: 1035993 (C4 (Web Text))
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.8327. Min Range: -0.8327
Max Act: 0.8327. Min Act: -0.0001
Data Index: 393215 (C4 (Web Text))
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.8327. Min Range: -0.8327
Max Act: 0.7851. Min Act: -0.0001
Data Index: 815016 (C4 (Web Text))
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.8327. Min Range: -0.8327
Max Act: 0.8047. Min Act: -0.0001
Data Index: 690497 (C4 (Web Text))
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.8327. Min Range: -0.8327
Max Act: 0.7478. Min Act: -0.0001
Data Index: 1227427 (C4 (Web Text))
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.8327. Min Range: -0.8327
Max Act: 0.7702. Min Act: -0.0001
Data Index: 1178289 (C4 (Web Text))
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.8327. Min Range: -0.8327
Max Act: 0.6795. Min Act: -0.0001
Data Index: 861489 (C4 (Web Text))
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.8327. Min Range: -0.8327
Max Act: 0.7870. Min Act: -0.0001
Data Index: 480782 (C4 (Web Text))
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.8327. Min Range: -0.8327
Max Act: 0.6863. Min Act: -0.0001
Data Index: 584247 (C4 (Web Text))
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.8327. Min Range: -0.8327
Max Act: 0.6548. Min Act: -0.0001
Data Index: 130974 (C4 (Web Text))
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.8327. Min Range: -0.8327
Max Act: 0.6974. Min Act: -0.0001
Data Index: 267176 (C4 (Web Text))
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.8327. Min Range: -0.8327
Max Act: 0.6943. Min Act: -0.0001
Data Index: 901922 (C4 (Web Text))
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.8327. Min Range: -0.8327
Max Act: 0.6356. Min Act: -0.0001
Data Index: 927866 (C4 (Web Text))
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.8327. Min Range: -0.8327
Max Act: 0.6838. Min Act: -0.0001
Data Index: 887837 (C4 (Web Text))
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.8327. Min Range: -0.8327
Max Act: 0.5978. Min Act: -0.0001
Data Index: 723148 (C4 (Web Text))
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.8327. Min Range: -0.8327
Max Act: 0.7006. Min Act: -0.0001
Data Index: 442578 (C4 (Web Text))
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.8327. Min Range: -0.8327
Max Act: 0.6382. Min Act: -0.0001
Data Index: 749606 (C4 (Web Text))
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.8327. Min Range: -0.8327
Max Act: 0.6569. Min Act: -0.0001
Data Index: 1190535 (C4 (Web Text))
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.8327. Min Range: -0.8327
Max Act: 0.6687. Min Act: -0.0001
Data Index: 1507545 (Python Code)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.8327. Min Range: -0.8327
Max Act: 0.6244. Min Act: -0.0001
Data Index: 120295 (C4 (Web Text))
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #19