Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3596 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 2.8095. Min Range: -2.8095
Max Act: 2.8095. Min Act: -0.0001
Data Index: 856896 (C4 (Web Text))
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8095. Min Range: -2.8095
Max Act: 2.5877. Min Act: -0.0001
Data Index: 792437 (C4 (Web Text))
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8095. Min Range: -2.8095
Max Act: 2.5663. Min Act: -0.0001
Data Index: 347857 (C4 (Web Text))
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8095. Min Range: -2.8095
Max Act: 2.3264. Min Act: -0.0001
Data Index: 805208 (C4 (Web Text))
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8095. Min Range: -2.8095
Max Act: 2.3089. Min Act: -0.0001
Data Index: 766411 (C4 (Web Text))
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8095. Min Range: -2.8095
Max Act: 2.5663. Min Act: -0.0001
Data Index: 61777 (C4 (Web Text))
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8095. Min Range: -2.8095
Max Act: 2.2507. Min Act: -0.0001
Data Index: 430812 (C4 (Web Text))
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8095. Min Range: -2.8095
Max Act: 2.2848. Min Act: -0.0001
Data Index: 25932 (C4 (Web Text))
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8095. Min Range: -2.8095
Max Act: 2.2789. Min Act: -0.0001
Data Index: 639411 (C4 (Web Text))
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8095. Min Range: -2.8095
Max Act: 2.2245. Min Act: -0.0001
Data Index: 647156 (C4 (Web Text))
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8095. Min Range: -2.8095
Max Act: 2.0274. Min Act: -0.0001
Data Index: 506149 (C4 (Web Text))
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8095. Min Range: -2.8095
Max Act: 2.1824. Min Act: -0.0001
Data Index: 1070076 (C4 (Web Text))
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8095. Min Range: -2.8095
Max Act: 2.0683. Min Act: -0.0001
Data Index: 1256033 (C4 (Web Text))
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8095. Min Range: -2.8095
Max Act: 2.2780. Min Act: -0.0001
Data Index: 1012850 (C4 (Web Text))
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8095. Min Range: -2.8095
Max Act: 1.9894. Min Act: -0.0001
Data Index: 236409 (C4 (Web Text))
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8095. Min Range: -2.8095
Max Act: 2.0836. Min Act: -0.0001
Data Index: 839629 (C4 (Web Text))
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8095. Min Range: -2.8095
Max Act: 2.0808. Min Act: -0.0001
Data Index: 1180617 (C4 (Web Text))
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8095. Min Range: -2.8095
Max Act: 1.9688. Min Act: -0.0001
Data Index: 597412 (C4 (Web Text))
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8095. Min Range: -2.8095
Max Act: 2.3283. Min Act: -0.0001
Data Index: 833699 (C4 (Web Text))
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8095. Min Range: -2.8095
Max Act: 2.0722. Min Act: -0.0001
Data Index: 749697 (C4 (Web Text))
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #19