Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3083 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 1.4719. Min Range: -1.4719
Max Act: 1.4719. Min Act: -0.0001
Data Index: 160758 (C4 (Web Text))
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.4719. Min Range: -1.4719
Max Act: 1.4006. Min Act: -0.0001
Data Index: 215673 (C4 (Web Text))
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.4719. Min Range: -1.4719
Max Act: 1.3530. Min Act: -0.0001
Data Index: 333097 (C4 (Web Text))
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.4719. Min Range: -1.4719
Max Act: 1.2954. Min Act: -0.0001
Data Index: 639390 (C4 (Web Text))
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.4719. Min Range: -1.4719
Max Act: 1.3562. Min Act: -0.0001
Data Index: 397335 (C4 (Web Text))
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.4719. Min Range: -1.4719
Max Act: 1.3679. Min Act: -0.0001
Data Index: 242812 (C4 (Web Text))
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.4719. Min Range: -1.4719
Max Act: 1.2519. Min Act: -0.0001
Data Index: 1149636 (C4 (Web Text))
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.4719. Min Range: -1.4719
Max Act: 1.2277. Min Act: -0.0001
Data Index: 304664 (C4 (Web Text))
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.4719. Min Range: -1.4719
Max Act: 1.1785. Min Act: -0.0001
Data Index: 1071446 (C4 (Web Text))
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.4719. Min Range: -1.4719
Max Act: 1.0910. Min Act: -0.0001
Data Index: 231960 (C4 (Web Text))
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.4719. Min Range: -1.4719
Max Act: 1.1899. Min Act: -0.0001
Data Index: 1358570 (C4 (Web Text))
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.4719. Min Range: -1.4719
Max Act: 1.1440. Min Act: -0.0001
Data Index: 73110 (C4 (Web Text))
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.4719. Min Range: -1.4719
Max Act: 1.1650. Min Act: -0.0001
Data Index: 525733 (C4 (Web Text))
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.4719. Min Range: -1.4719
Max Act: 1.1257. Min Act: -0.0001
Data Index: 282414 (C4 (Web Text))
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.4719. Min Range: -1.4719
Max Act: 1.1540. Min Act: -0.0001
Data Index: 864153 (C4 (Web Text))
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.4719. Min Range: -1.4719
Max Act: 1.1145. Min Act: -0.0001
Data Index: 136896 (C4 (Web Text))
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.4719. Min Range: -1.4719
Max Act: 1.1664. Min Act: -0.0001
Data Index: 323666 (C4 (Web Text))
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.4719. Min Range: -1.4719
Max Act: 1.1067. Min Act: -0.0001
Data Index: 595140 (C4 (Web Text))
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.4719. Min Range: -1.4719
Max Act: 1.1456. Min Act: -0.0001
Data Index: 890683 (C4 (Web Text))
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.4719. Min Range: -1.4719
Max Act: 1.1063. Min Act: -0.0001
Data Index: 1542235 (Python Code)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #19