Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 4016 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 0.2017. Min Range: -0.2017
Max Act: 0.1987. Min Act: -0.0001
Data Index: 615061 (C4 (Web Text))
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.2017. Min Range: -0.2017
Max Act: 0.1928. Min Act: -0.0001
Data Index: 1043243 (C4 (Web Text))
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.2017. Min Range: -0.2017
Max Act: 0.1778. Min Act: -0.0001
Data Index: 799996 (C4 (Web Text))
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.2017. Min Range: -0.2017
Max Act: 0.2017. Min Act: -0.0001
Data Index: 287984 (C4 (Web Text))
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.2017. Min Range: -0.2017
Max Act: 0.1807. Min Act: -0.0001
Data Index: 1148436 (C4 (Web Text))
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.2017. Min Range: -0.2017
Max Act: 0.1745. Min Act: -0.0001
Data Index: 243833 (C4 (Web Text))
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.2017. Min Range: -0.2017
Max Act: 0.1771. Min Act: -0.0001
Data Index: 782050 (C4 (Web Text))
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.2017. Min Range: -0.2017
Max Act: 0.1584. Min Act: -0.0001
Data Index: 83007 (C4 (Web Text))
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.2017. Min Range: -0.2017
Max Act: 0.1683. Min Act: -0.0001
Data Index: 706030 (C4 (Web Text))
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.2017. Min Range: -0.2017
Max Act: 0.1620. Min Act: -0.0001
Data Index: 42830 (C4 (Web Text))
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.2017. Min Range: -0.2017
Max Act: 0.1675. Min Act: -0.0001
Data Index: 230718 (C4 (Web Text))
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.2017. Min Range: -0.2017
Max Act: 0.1705. Min Act: -0.0001
Data Index: 1584636 (Python Code)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.2017. Min Range: -0.2017
Max Act: 0.1607. Min Act: -0.0001
Data Index: 199126 (C4 (Web Text))
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.2017. Min Range: -0.2017
Max Act: 0.1585. Min Act: -0.0001
Data Index: 978694 (C4 (Web Text))
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.2017. Min Range: -0.2017
Max Act: 0.1605. Min Act: -0.0001
Data Index: 458134 (C4 (Web Text))
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.2017. Min Range: -0.2017
Max Act: 0.1566. Min Act: -0.0001
Data Index: 479447 (C4 (Web Text))
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.2017. Min Range: -0.2017
Max Act: 0.1640. Min Act: -0.0001
Data Index: 347980 (C4 (Web Text))
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.2017. Min Range: -0.2017
Max Act: 0.1530. Min Act: -0.0001
Data Index: 1261527 (C4 (Web Text))
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.2017. Min Range: -0.2017
Max Act: 0.1518. Min Act: -0.0001
Data Index: 1418266 (Python Code)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.2017. Min Range: -0.2017
Max Act: 0.1446. Min Act: -0.0001
Data Index: 600137 (C4 (Web Text))
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #19