Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3910 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 0.2609. Min Range: -0.2609
Max Act: 0.2609. Min Act: -0.0001
Data Index: 588734 (C4 (Web Text))
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.2609. Min Range: -0.2609
Max Act: 0.2509. Min Act: -0.0001
Data Index: 312186 (C4 (Web Text))
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.2609. Min Range: -0.2609
Max Act: 0.2285. Min Act: -0.0001
Data Index: 200743 (C4 (Web Text))
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.2609. Min Range: -0.2609
Max Act: 0.2036. Min Act: -0.0001
Data Index: 971266 (C4 (Web Text))
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.2609. Min Range: -0.2609
Max Act: 0.2151. Min Act: -0.0001
Data Index: 1076069 (C4 (Web Text))
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.2609. Min Range: -0.2609
Max Act: 0.2176. Min Act: -0.0001
Data Index: 657727 (C4 (Web Text))
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.2609. Min Range: -0.2609
Max Act: 0.2072. Min Act: -0.0001
Data Index: 256043 (C4 (Web Text))
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.2609. Min Range: -0.2609
Max Act: 0.1718. Min Act: -0.0001
Data Index: 433868 (C4 (Web Text))
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.2609. Min Range: -0.2609
Max Act: 0.1915. Min Act: -0.0001
Data Index: 1284849 (C4 (Web Text))
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.2609. Min Range: -0.2609
Max Act: 0.1852. Min Act: -0.0001
Data Index: 721954 (C4 (Web Text))
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.2609. Min Range: -0.2609
Max Act: 0.1850. Min Act: -0.0001
Data Index: 224067 (C4 (Web Text))
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.2609. Min Range: -0.2609
Max Act: 0.1825. Min Act: -0.0001
Data Index: 782587 (C4 (Web Text))
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.2609. Min Range: -0.2609
Max Act: 0.1696. Min Act: -0.0001
Data Index: 438627 (C4 (Web Text))
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.2609. Min Range: -0.2609
Max Act: 0.1807. Min Act: -0.0001
Data Index: 801000 (C4 (Web Text))
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.2609. Min Range: -0.2609
Max Act: 0.1736. Min Act: -0.0001
Data Index: 1238274 (C4 (Web Text))
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.2609. Min Range: -0.2609
Max Act: 0.1850. Min Act: -0.0001
Data Index: 58063 (C4 (Web Text))
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.2609. Min Range: -0.2609
Max Act: 0.1611. Min Act: -0.0001
Data Index: 1129305 (C4 (Web Text))
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.2609. Min Range: -0.2609
Max Act: 0.1614. Min Act: -0.0001
Data Index: 626739 (C4 (Web Text))
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.2609. Min Range: -0.2609
Max Act: 0.1494. Min Act: -0.0001
Data Index: 4307 (C4 (Web Text))
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.2609. Min Range: -0.2609
Max Act: 0.1705. Min Act: -0.0001
Data Index: 79902 (C4 (Web Text))
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #19