Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2970 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 2.2404. Min Range: -2.2404
Max Act: 2.2404. Min Act: -0.0002
Data Index: 205743 (C4 (Web Text))
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.2404. Min Range: -2.2404
Max Act: 1.6297. Min Act: -0.0002
Data Index: 815979 (C4 (Web Text))
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.2404. Min Range: -2.2404
Max Act: 1.7295. Min Act: -0.0002
Data Index: 766659 (C4 (Web Text))
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.2404. Min Range: -2.2404
Max Act: 1.4850. Min Act: -0.0002
Data Index: 1121061 (C4 (Web Text))
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.2404. Min Range: -2.2404
Max Act: 1.6115. Min Act: -0.0002
Data Index: 589723 (C4 (Web Text))
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.2404. Min Range: -2.2404
Max Act: 1.5042. Min Act: -0.0002
Data Index: 141787 (C4 (Web Text))
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.2404. Min Range: -2.2404
Max Act: 1.5997. Min Act: -0.0002
Data Index: 1295364 (C4 (Web Text))
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.2404. Min Range: -2.2404
Max Act: 1.6492. Min Act: -0.0002
Data Index: 1039735 (C4 (Web Text))
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.2404. Min Range: -2.2404
Max Act: 1.5590. Min Act: -0.0002
Data Index: 388592 (C4 (Web Text))
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.2404. Min Range: -2.2404
Max Act: 1.6364. Min Act: -0.0002
Data Index: 150241 (C4 (Web Text))
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.2404. Min Range: -2.2404
Max Act: 1.3755. Min Act: -0.0002
Data Index: 210431 (C4 (Web Text))
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.2404. Min Range: -2.2404
Max Act: 1.5557. Min Act: -0.0002
Data Index: 603584 (C4 (Web Text))
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.2404. Min Range: -2.2404
Max Act: 1.2817. Min Act: -0.0002
Data Index: 819180 (C4 (Web Text))
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.2404. Min Range: -2.2404
Max Act: 1.4196. Min Act: -0.0002
Data Index: 505027 (C4 (Web Text))
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.2404. Min Range: -2.2404
Max Act: 1.3887. Min Act: -0.0002
Data Index: 409741 (C4 (Web Text))
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.2404. Min Range: -2.2404
Max Act: 1.2216. Min Act: -0.0002
Data Index: 994029 (C4 (Web Text))
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.2404. Min Range: -2.2404
Max Act: 1.3565. Min Act: -0.0002
Data Index: 632966 (C4 (Web Text))
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.2404. Min Range: -2.2404
Max Act: 1.4550. Min Act: -0.0002
Data Index: 843692 (C4 (Web Text))
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.2404. Min Range: -2.2404
Max Act: 1.2591. Min Act: -0.0002
Data Index: 150591 (C4 (Web Text))
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.2404. Min Range: -2.2404
Max Act: 1.4757. Min Act: -0.0002
Data Index: 360115 (C4 (Web Text))
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #19