Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3903 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 0.0881. Min Range: -0.0881
Max Act: 0.0881. Min Act: -0.0001
Data Index: 761407 (C4 (Web Text))
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.0881. Min Range: -0.0881
Max Act: 0.0852. Min Act: -0.0001
Data Index: 458723 (C4 (Web Text))
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.0881. Min Range: -0.0881
Max Act: 0.0857. Min Act: -0.0001
Data Index: 1130866 (C4 (Web Text))
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.0881. Min Range: -0.0881
Max Act: 0.0739. Min Act: -0.0001
Data Index: 1329005 (C4 (Web Text))
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.0881. Min Range: -0.0881
Max Act: 0.0838. Min Act: -0.0001
Data Index: 434469 (C4 (Web Text))
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.0881. Min Range: -0.0881
Max Act: 0.0677. Min Act: -0.0001
Data Index: 1227777 (C4 (Web Text))
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.0881. Min Range: -0.0881
Max Act: 0.0729. Min Act: -0.0001
Data Index: 230197 (C4 (Web Text))
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.0881. Min Range: -0.0881
Max Act: 0.0713. Min Act: -0.0001
Data Index: 1181535 (C4 (Web Text))
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.0881. Min Range: -0.0881
Max Act: 0.0716. Min Act: -0.0001
Data Index: 146308 (C4 (Web Text))
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.0881. Min Range: -0.0881
Max Act: 0.0714. Min Act: -0.0001
Data Index: 912574 (C4 (Web Text))
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.0881. Min Range: -0.0881
Max Act: 0.0709. Min Act: -0.0001
Data Index: 814124 (C4 (Web Text))
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.0881. Min Range: -0.0881
Max Act: 0.0697. Min Act: -0.0001
Data Index: 331405 (C4 (Web Text))
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.0881. Min Range: -0.0881
Max Act: 0.0642. Min Act: -0.0001
Data Index: 458431 (C4 (Web Text))
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.0881. Min Range: -0.0881
Max Act: 0.0683. Min Act: -0.0001
Data Index: 1572700 (Python Code)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.0881. Min Range: -0.0881
Max Act: 0.0662. Min Act: -0.0001
Data Index: 1287832 (C4 (Web Text))
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.0881. Min Range: -0.0881
Max Act: 0.0679. Min Act: -0.0001
Data Index: 640067 (C4 (Web Text))
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.0881. Min Range: -0.0881
Max Act: 0.0690. Min Act: -0.0001
Data Index: 276306 (C4 (Web Text))
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.0881. Min Range: -0.0881
Max Act: 0.0763. Min Act: -0.0001
Data Index: 1100137 (C4 (Web Text))
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.0881. Min Range: -0.0881
Max Act: 0.0632. Min Act: -0.0001
Data Index: 850050 (C4 (Web Text))
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.0881. Min Range: -0.0881
Max Act: 0.0631. Min Act: -0.0001
Data Index: 214108 (C4 (Web Text))
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #19