Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1383 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 0.1029. Min Range: -0.1029
Max Act: 0.1029. Min Act: -0.0002
Data Index: 444104 (C4 (Web Text))
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.1029. Min Range: -0.1029
Max Act: 0.0983. Min Act: -0.0002
Data Index: 890062 (C4 (Web Text))
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.1029. Min Range: -0.1029
Max Act: 0.0910. Min Act: -0.0002
Data Index: 60658 (C4 (Web Text))
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.1029. Min Range: -0.1029
Max Act: 0.0924. Min Act: -0.0002
Data Index: 11752 (C4 (Web Text))
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.1029. Min Range: -0.1029
Max Act: 0.0839. Min Act: -0.0002
Data Index: 1337838 (C4 (Web Text))
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.1029. Min Range: -0.1029
Max Act: 0.0796. Min Act: -0.0002
Data Index: 832629 (C4 (Web Text))
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.1029. Min Range: -0.1029
Max Act: 0.0837. Min Act: -0.0002
Data Index: 1212255 (C4 (Web Text))
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.1029. Min Range: -0.1029
Max Act: 0.0858. Min Act: -0.0002
Data Index: 425265 (C4 (Web Text))
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.1029. Min Range: -0.1029
Max Act: 0.0828. Min Act: -0.0002
Data Index: 1154391 (C4 (Web Text))
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.1029. Min Range: -0.1029
Max Act: 0.0841. Min Act: -0.0002
Data Index: 1325150 (C4 (Web Text))
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.1029. Min Range: -0.1029
Max Act: 0.0795. Min Act: -0.0002
Data Index: 605770 (C4 (Web Text))
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.1029. Min Range: -0.1029
Max Act: 0.0855. Min Act: -0.0002
Data Index: 474973 (C4 (Web Text))
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.1029. Min Range: -0.1029
Max Act: 0.0817. Min Act: -0.0002
Data Index: 953955 (C4 (Web Text))
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.1029. Min Range: -0.1029
Max Act: 0.0764. Min Act: -0.0002
Data Index: 637354 (C4 (Web Text))
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.1029. Min Range: -0.1029
Max Act: 0.0788. Min Act: -0.0002
Data Index: 851561 (C4 (Web Text))
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.1029. Min Range: -0.1029
Max Act: 0.0786. Min Act: -0.0002
Data Index: 1314688 (C4 (Web Text))
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.1029. Min Range: -0.1029
Max Act: 0.0851. Min Act: -0.0002
Data Index: 40323 (C4 (Web Text))
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.1029. Min Range: -0.1029
Max Act: 0.0770. Min Act: -0.0002
Data Index: 17866 (C4 (Web Text))
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.1029. Min Range: -0.1029
Max Act: 0.0824. Min Act: -0.0002
Data Index: 705495 (C4 (Web Text))
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.1029. Min Range: -0.1029
Max Act: 0.0818. Min Act: -0.0002
Data Index: 492663 (C4 (Web Text))
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #19