Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 5105 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 2.1859. Min Range: -2.1859
Max Act: 2.0098. Min Act: -0.0001
Data Index: 1263219 (C4 (Web Text))
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.1859. Min Range: -2.1859
Max Act: 2.0073. Min Act: -0.0001
Data Index: 242868 (C4 (Web Text))
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.1859. Min Range: -2.1859
Max Act: 2.1859. Min Act: -0.0001
Data Index: 1038134 (C4 (Web Text))
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.1859. Min Range: -2.1859
Max Act: 1.9101. Min Act: -0.0001
Data Index: 685797 (C4 (Web Text))
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.1859. Min Range: -2.1859
Max Act: 1.8990. Min Act: -0.0001
Data Index: 535919 (C4 (Web Text))
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.1859. Min Range: -2.1859
Max Act: 1.6907. Min Act: -0.0001
Data Index: 211471 (C4 (Web Text))
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.1859. Min Range: -2.1859
Max Act: 1.6634. Min Act: -0.0001
Data Index: 591525 (C4 (Web Text))
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.1859. Min Range: -2.1859
Max Act: 1.6680. Min Act: -0.0001
Data Index: 855915 (C4 (Web Text))
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.1859. Min Range: -2.1859
Max Act: 1.9200. Min Act: -0.0001
Data Index: 751153 (C4 (Web Text))
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.1859. Min Range: -2.1859
Max Act: 1.8108. Min Act: -0.0001
Data Index: 1027497 (C4 (Web Text))
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.1859. Min Range: -2.1859
Max Act: 1.9102. Min Act: -0.0001
Data Index: 21857 (C4 (Web Text))
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.1859. Min Range: -2.1859
Max Act: 1.8965. Min Act: -0.0001
Data Index: 143645 (C4 (Web Text))
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.1859. Min Range: -2.1859
Max Act: 1.7864. Min Act: -0.0001
Data Index: 462038 (C4 (Web Text))
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.1859. Min Range: -2.1859
Max Act: 1.7826. Min Act: -0.0001
Data Index: 307264 (C4 (Web Text))
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.1859. Min Range: -2.1859
Max Act: 1.5558. Min Act: -0.0001
Data Index: 479352 (C4 (Web Text))
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.1859. Min Range: -2.1859
Max Act: 1.6016. Min Act: -0.0001
Data Index: 466190 (C4 (Web Text))
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.1859. Min Range: -2.1859
Max Act: 1.6522. Min Act: -0.0001
Data Index: 480178 (C4 (Web Text))
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.1859. Min Range: -2.1859
Max Act: 1.7019. Min Act: -0.0001
Data Index: 74910 (C4 (Web Text))
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.1859. Min Range: -2.1859
Max Act: 1.6777. Min Act: -0.0001
Data Index: 989164 (C4 (Web Text))
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.1859. Min Range: -2.1859
Max Act: 1.7398. Min Act: -0.0001
Data Index: 1087311 (C4 (Web Text))
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #19