Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2645 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 0.1002. Min Range: -0.1002
Max Act: 0.1002. Min Act: -0.0001
Data Index: 947726 (C4 (Web Text))
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.1002. Min Range: -0.1002
Max Act: 0.0839. Min Act: -0.0001
Data Index: 1351442 (C4 (Web Text))
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.1002. Min Range: -0.1002
Max Act: 0.0846. Min Act: -0.0001
Data Index: 1241424 (C4 (Web Text))
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.1002. Min Range: -0.1002
Max Act: 0.0740. Min Act: -0.0001
Data Index: 111860 (C4 (Web Text))
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.1002. Min Range: -0.1002
Max Act: 0.0855. Min Act: -0.0001
Data Index: 355182 (C4 (Web Text))
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.1002. Min Range: -0.1002
Max Act: 0.0716. Min Act: -0.0001
Data Index: 142691 (C4 (Web Text))
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.1002. Min Range: -0.1002
Max Act: 0.0771. Min Act: -0.0001
Data Index: 272687 (C4 (Web Text))
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.1002. Min Range: -0.1002
Max Act: 0.0774. Min Act: -0.0001
Data Index: 480725 (C4 (Web Text))
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.1002. Min Range: -0.1002
Max Act: 0.0892. Min Act: -0.0001
Data Index: 685943 (C4 (Web Text))
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.1002. Min Range: -0.1002
Max Act: 0.0783. Min Act: -0.0001
Data Index: 1034152 (C4 (Web Text))
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.1002. Min Range: -0.1002
Max Act: 0.0835. Min Act: -0.0001
Data Index: 443647 (C4 (Web Text))
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.1002. Min Range: -0.1002
Max Act: 0.0772. Min Act: -0.0001
Data Index: 1018032 (C4 (Web Text))
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.1002. Min Range: -0.1002
Max Act: 0.0783. Min Act: -0.0001
Data Index: 915528 (C4 (Web Text))
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.1002. Min Range: -0.1002
Max Act: 0.0681. Min Act: -0.0001
Data Index: 1280761 (C4 (Web Text))
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.1002. Min Range: -0.1002
Max Act: 0.0707. Min Act: -0.0001
Data Index: 938833 (C4 (Web Text))
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.1002. Min Range: -0.1002
Max Act: 0.0701. Min Act: -0.0001
Data Index: 1273706 (C4 (Web Text))
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.1002. Min Range: -0.1002
Max Act: 0.0674. Min Act: -0.0001
Data Index: 1172211 (C4 (Web Text))
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.1002. Min Range: -0.1002
Max Act: 0.0736. Min Act: -0.0001
Data Index: 1040755 (C4 (Web Text))
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.1002. Min Range: -0.1002
Max Act: 0.0683. Min Act: -0.0001
Data Index: 153539 (C4 (Web Text))
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.1002. Min Range: -0.1002
Max Act: 0.0707. Min Act: -0.0001
Data Index: 1119586 (C4 (Web Text))
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #19