Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3218 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 1.8818. Min Range: -1.8818
Max Act: 1.8818. Min Act: -0.0001
Data Index: 1034772 (C4 (Web Text))
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.8818. Min Range: -1.8818
Max Act: 1.6842. Min Act: -0.0001
Data Index: 1160779 (C4 (Web Text))
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.8818. Min Range: -1.8818
Max Act: 1.5623. Min Act: -0.0002
Data Index: 475598 (C4 (Web Text))
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.8818. Min Range: -1.8818
Max Act: 1.5768. Min Act: -0.0001
Data Index: 248674 (C4 (Web Text))
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.8818. Min Range: -1.8818
Max Act: 1.4789. Min Act: -0.0002
Data Index: 885133 (C4 (Web Text))
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.8818. Min Range: -1.8818
Max Act: 1.5218. Min Act: -0.0001
Data Index: 818459 (C4 (Web Text))
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.8818. Min Range: -1.8818
Max Act: 1.6282. Min Act: -0.0001
Data Index: 333352 (C4 (Web Text))
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.8818. Min Range: -1.8818
Max Act: 1.6546. Min Act: -0.0001
Data Index: 784894 (C4 (Web Text))
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.8818. Min Range: -1.8818
Max Act: 1.5160. Min Act: -0.0001
Data Index: 412358 (C4 (Web Text))
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.8818. Min Range: -1.8818
Max Act: 1.5242. Min Act: -0.0001
Data Index: 1127850 (C4 (Web Text))
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.8818. Min Range: -1.8818
Max Act: 1.5178. Min Act: -0.0001
Data Index: 115952 (C4 (Web Text))
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.8818. Min Range: -1.8818
Max Act: 1.5426. Min Act: -0.0002
Data Index: 75909 (C4 (Web Text))
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.8818. Min Range: -1.8818
Max Act: 1.5017. Min Act: -0.0001
Data Index: 110838 (C4 (Web Text))
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.8818. Min Range: -1.8818
Max Act: 1.5753. Min Act: -0.0001
Data Index: 299604 (C4 (Web Text))
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.8818. Min Range: -1.8818
Max Act: 1.4993. Min Act: -0.0002
Data Index: 1304514 (C4 (Web Text))
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.8818. Min Range: -1.8818
Max Act: 1.4620. Min Act: -0.0002
Data Index: 1123086 (C4 (Web Text))
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.8818. Min Range: -1.8818
Max Act: 1.5387. Min Act: -0.0001
Data Index: 825743 (C4 (Web Text))
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.8818. Min Range: -1.8818
Max Act: 1.4770. Min Act: -0.0001
Data Index: 171443 (C4 (Web Text))
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.8818. Min Range: -1.8818
Max Act: 1.3758. Min Act: -0.0001
Data Index: 872336 (C4 (Web Text))
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.8818. Min Range: -1.8818
Max Act: 1.4142. Min Act: -0.0002
Data Index: 612768 (C4 (Web Text))
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #19