Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 626 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 0.1201. Min Range: -0.1201
Max Act: 0.1201. Min Act: -0.0001
Data Index: 834412 (C4 (Web Text))
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.1201. Min Range: -0.1201
Max Act: 0.1031. Min Act: -0.0001
Data Index: 397281 (C4 (Web Text))
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.1201. Min Range: -0.1201
Max Act: 0.1052. Min Act: -0.0001
Data Index: 667561 (C4 (Web Text))
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.1201. Min Range: -0.1201
Max Act: 0.1034. Min Act: -0.0001
Data Index: 1275133 (C4 (Web Text))
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.1201. Min Range: -0.1201
Max Act: 0.0953. Min Act: -0.0001
Data Index: 357398 (C4 (Web Text))
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.1201. Min Range: -0.1201
Max Act: 0.0907. Min Act: -0.0001
Data Index: 987752 (C4 (Web Text))
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.1201. Min Range: -0.1201
Max Act: 0.1038. Min Act: -0.0001
Data Index: 1603548 (Python Code)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.1201. Min Range: -0.1201
Max Act: 0.0970. Min Act: -0.0001
Data Index: 726590 (C4 (Web Text))
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.1201. Min Range: -0.1201
Max Act: 0.0935. Min Act: -0.0001
Data Index: 125494 (C4 (Web Text))
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.1201. Min Range: -0.1201
Max Act: 0.1043. Min Act: -0.0001
Data Index: 1289026 (C4 (Web Text))
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.1201. Min Range: -0.1201
Max Act: 0.0970. Min Act: -0.0001
Data Index: 813854 (C4 (Web Text))
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.1201. Min Range: -0.1201
Max Act: 0.0937. Min Act: -0.0001
Data Index: 868604 (C4 (Web Text))
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.1201. Min Range: -0.1201
Max Act: 0.0992. Min Act: -0.0001
Data Index: 815413 (C4 (Web Text))
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.1201. Min Range: -0.1201
Max Act: 0.0877. Min Act: -0.0001
Data Index: 399644 (C4 (Web Text))
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.1201. Min Range: -0.1201
Max Act: 0.0940. Min Act: -0.0001
Data Index: 1463981 (Python Code)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.1201. Min Range: -0.1201
Max Act: 0.0910. Min Act: -0.0001
Data Index: 1060715 (C4 (Web Text))
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.1201. Min Range: -0.1201
Max Act: 0.0971. Min Act: -0.0001
Data Index: 318591 (C4 (Web Text))
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.1201. Min Range: -0.1201
Max Act: 0.0985. Min Act: -0.0001
Data Index: 1202874 (C4 (Web Text))
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.1201. Min Range: -0.1201
Max Act: 0.0893. Min Act: -0.0001
Data Index: 306456 (C4 (Web Text))
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.1201. Min Range: -0.1201
Max Act: 0.0897. Min Act: -0.0001
Data Index: 1008592 (C4 (Web Text))
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #19