Model: SoLU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 663 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')
Text #0
Max Range: 0.1000. Min Range: -0.1000
Max Act: 0.1000. Min Act: -0.0003
Data Index: 392454 (C4 (Web Text))
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.1000. Min Range: -0.1000
Max Act: 0.0892. Min Act: -0.0003
Data Index: 16961 (C4 (Web Text))
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.1000. Min Range: -0.1000
Max Act: 0.0896. Min Act: -0.0003
Data Index: 398398 (C4 (Web Text))
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.1000. Min Range: -0.1000
Max Act: 0.0823. Min Act: -0.0003
Data Index: 6268 (C4 (Web Text))
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.1000. Min Range: -0.1000
Max Act: 0.0829. Min Act: -0.0003
Data Index: 567108 (C4 (Web Text))
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.1000. Min Range: -0.1000
Max Act: 0.0802. Min Act: -0.0004
Data Index: 653169 (C4 (Web Text))
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.1000. Min Range: -0.1000
Max Act: 0.0778. Min Act: -0.0004
Data Index: 1241180 (C4 (Web Text))
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.1000. Min Range: -0.1000
Max Act: 0.0788. Min Act: -0.0003
Data Index: 73845 (C4 (Web Text))
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.1000. Min Range: -0.1000
Max Act: 0.0753. Min Act: -0.0003
Data Index: 433185 (C4 (Web Text))
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.1000. Min Range: -0.1000
Max Act: 0.0716. Min Act: -0.0003
Data Index: 1053875 (C4 (Web Text))
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.1000. Min Range: -0.1000
Max Act: 0.0768. Min Act: -0.0003
Data Index: 1287858 (C4 (Web Text))
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.1000. Min Range: -0.1000
Max Act: 0.0734. Min Act: -0.0003
Data Index: 1072065 (C4 (Web Text))
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.1000. Min Range: -0.1000
Max Act: 0.0746. Min Act: -0.0003
Data Index: 1337540 (C4 (Web Text))
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.1000. Min Range: -0.1000
Max Act: 0.0739. Min Act: -0.0003
Data Index: 48618 (C4 (Web Text))
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.1000. Min Range: -0.1000
Max Act: 0.0741. Min Act: -0.0003
Data Index: 390675 (C4 (Web Text))
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.1000. Min Range: -0.1000
Max Act: 0.0734. Min Act: -0.0003
Data Index: 856770 (C4 (Web Text))
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.1000. Min Range: -0.1000
Max Act: 0.0721. Min Act: -0.0003
Data Index: 70643 (C4 (Web Text))
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.1000. Min Range: -0.1000
Max Act: 0.0721. Min Act: -0.0003
Data Index: 1317866 (C4 (Web Text))
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.1000. Min Range: -0.1000
Max Act: 0.0730. Min Act: -0.0003
Data Index: 208324 (C4 (Web Text))
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.1000. Min Range: -0.1000
Max Act: 0.0686. Min Act: -0.0003
Data Index: 668573 (C4 (Web Text))
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #19