Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1482 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 2.7732. Min Range: -2.7732
Max Act: 2.5751. Min Act: -0.0001
Data Index: 764936 (C4 (Web Text))
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7732. Min Range: -2.7732
Max Act: 2.6782. Min Act: -0.0000
Data Index: 41252 (C4 (Web Text))
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7732. Min Range: -2.7732
Max Act: 2.6368. Min Act: -0.0001
Data Index: 338523 (C4 (Web Text))
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7732. Min Range: -2.7732
Max Act: 2.7732. Min Act: -0.0001
Data Index: 257727 (C4 (Web Text))
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7732. Min Range: -2.7732
Max Act: 2.6046. Min Act: -0.0001
Data Index: 1181087 (C4 (Web Text))
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7732. Min Range: -2.7732
Max Act: 2.6801. Min Act: -0.0001
Data Index: 1193878 (C4 (Web Text))
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7732. Min Range: -2.7732
Max Act: 2.4235. Min Act: -0.0001
Data Index: 503620 (C4 (Web Text))
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7732. Min Range: -2.7732
Max Act: 2.5513. Min Act: -0.0001
Data Index: 353621 (C4 (Web Text))
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7732. Min Range: -2.7732
Max Act: 2.5178. Min Act: -0.0001
Data Index: 775853 (C4 (Web Text))
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7732. Min Range: -2.7732
Max Act: 2.5102. Min Act: -0.0001
Data Index: 85197 (C4 (Web Text))
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7732. Min Range: -2.7732
Max Act: 2.3909. Min Act: -0.0000
Data Index: 13449 (C4 (Web Text))
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7732. Min Range: -2.7732
Max Act: 2.3503. Min Act: -0.0000
Data Index: 1101490 (C4 (Web Text))
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7732. Min Range: -2.7732
Max Act: 2.5519. Min Act: -0.0001
Data Index: 1201024 (C4 (Web Text))
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7732. Min Range: -2.7732
Max Act: 2.4275. Min Act: -0.0001
Data Index: 856307 (C4 (Web Text))
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7732. Min Range: -2.7732
Max Act: 2.3970. Min Act: -0.0001
Data Index: 157709 (C4 (Web Text))
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7732. Min Range: -2.7732
Max Act: 2.3546. Min Act: -0.0001
Data Index: 530110 (C4 (Web Text))
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7732. Min Range: -2.7732
Max Act: 2.1884. Min Act: -0.0000
Data Index: 692110 (C4 (Web Text))
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7732. Min Range: -2.7732
Max Act: 2.0839. Min Act: -0.0001
Data Index: 842336 (C4 (Web Text))
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7732. Min Range: -2.7732
Max Act: 2.2001. Min Act: -0.0001
Data Index: 783691 (C4 (Web Text))
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7732. Min Range: -2.7732
Max Act: 2.3211. Min Act: -0.0001
Data Index: 285364 (C4 (Web Text))
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #19