Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3858 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 2.8062. Min Range: -2.8062
Max Act: 2.8062. Min Act: -0.0001
Data Index: 968850 (C4 (Web Text))
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8062. Min Range: -2.8062
Max Act: 2.7206. Min Act: -0.0001
Data Index: 446239 (C4 (Web Text))
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8062. Min Range: -2.8062
Max Act: 2.5715. Min Act: -0.0001
Data Index: 360708 (C4 (Web Text))
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8062. Min Range: -2.8062
Max Act: 2.6817. Min Act: -0.0001
Data Index: 301368 (C4 (Web Text))
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8062. Min Range: -2.8062
Max Act: 2.5779. Min Act: -0.0001
Data Index: 649948 (C4 (Web Text))
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8062. Min Range: -2.8062
Max Act: 2.6208. Min Act: -0.0001
Data Index: 499029 (C4 (Web Text))
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8062. Min Range: -2.8062
Max Act: 2.4019. Min Act: -0.0001
Data Index: 133739 (C4 (Web Text))
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8062. Min Range: -2.8062
Max Act: 2.3824. Min Act: -0.0001
Data Index: 438080 (C4 (Web Text))
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8062. Min Range: -2.8062
Max Act: 2.6410. Min Act: -0.0001
Data Index: 337841 (C4 (Web Text))
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8062. Min Range: -2.8062
Max Act: 2.3289. Min Act: -0.0001
Data Index: 759912 (C4 (Web Text))
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8062. Min Range: -2.8062
Max Act: 2.4504. Min Act: -0.0001
Data Index: 443715 (C4 (Web Text))
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8062. Min Range: -2.8062
Max Act: 2.5429. Min Act: -0.0001
Data Index: 155389 (C4 (Web Text))
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8062. Min Range: -2.8062
Max Act: 2.4129. Min Act: -0.0001
Data Index: 8091 (C4 (Web Text))
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8062. Min Range: -2.8062
Max Act: 2.4009. Min Act: -0.0001
Data Index: 1373914 (Python Code)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8062. Min Range: -2.8062
Max Act: 2.3882. Min Act: -0.0001
Data Index: 872657 (C4 (Web Text))
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8062. Min Range: -2.8062
Max Act: 2.2567. Min Act: -0.0001
Data Index: 1196613 (C4 (Web Text))
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8062. Min Range: -2.8062
Max Act: 2.0879. Min Act: -0.0001
Data Index: 1476178 (Python Code)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8062. Min Range: -2.8062
Max Act: 2.3759. Min Act: -0.0001
Data Index: 14074 (C4 (Web Text))
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8062. Min Range: -2.8062
Max Act: 2.3633. Min Act: -0.0001
Data Index: 1341115 (C4 (Web Text))
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8062. Min Range: -2.8062
Max Act: 2.2305. Min Act: -0.0001
Data Index: 721991 (C4 (Web Text))
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #19