Model: SoLU Model: 6 Layers, 3072 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1372 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')
Text #0
Max Range: 0.2457. Min Range: -0.2457
Max Act: 0.2457. Min Act: -0.0001
Data Index: 859660 (C4 (Web Text))
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.2457. Min Range: -0.2457
Max Act: 0.2408. Min Act: -0.0001
Data Index: 1285656 (C4 (Web Text))
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.2457. Min Range: -0.2457
Max Act: 0.2256. Min Act: -0.0001
Data Index: 1490826 (Python Code)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.2457. Min Range: -0.2457
Max Act: 0.2138. Min Act: -0.0001
Data Index: 1313642 (C4 (Web Text))
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.2457. Min Range: -0.2457
Max Act: 0.2194. Min Act: -0.0001
Data Index: 1140431 (C4 (Web Text))
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.2457. Min Range: -0.2457
Max Act: 0.2034. Min Act: -0.0001
Data Index: 1007275 (C4 (Web Text))
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.2457. Min Range: -0.2457
Max Act: 0.2056. Min Act: -0.0001
Data Index: 866469 (C4 (Web Text))
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.2457. Min Range: -0.2457
Max Act: 0.1832. Min Act: -0.0001
Data Index: 1132573 (C4 (Web Text))
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.2457. Min Range: -0.2457
Max Act: 0.1992. Min Act: -0.0001
Data Index: 418532 (C4 (Web Text))
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.2457. Min Range: -0.2457
Max Act: 0.1995. Min Act: -0.0001
Data Index: 1545256 (Python Code)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.2457. Min Range: -0.2457
Max Act: 0.2023. Min Act: -0.0001
Data Index: 875727 (C4 (Web Text))
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.2457. Min Range: -0.2457
Max Act: 0.1871. Min Act: -0.0001
Data Index: 1046468 (C4 (Web Text))
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.2457. Min Range: -0.2457
Max Act: 0.1936. Min Act: -0.0001
Data Index: 227590 (C4 (Web Text))
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.2457. Min Range: -0.2457
Max Act: 0.1931. Min Act: -0.0001
Data Index: 362417 (C4 (Web Text))
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.2457. Min Range: -0.2457
Max Act: 0.1918. Min Act: -0.0001
Data Index: 522753 (C4 (Web Text))
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.2457. Min Range: -0.2457
Max Act: 0.1828. Min Act: -0.0001
Data Index: 1212932 (C4 (Web Text))
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.2457. Min Range: -0.2457
Max Act: 0.1880. Min Act: -0.0001
Data Index: 1053732 (C4 (Web Text))
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.2457. Min Range: -0.2457
Max Act: 0.1919. Min Act: -0.0001
Data Index: 1188839 (C4 (Web Text))
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.2457. Min Range: -0.2457
Max Act: 0.1845. Min Act: -0.0001
Data Index: 145278 (C4 (Web Text))
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.2457. Min Range: -0.2457
Max Act: 0.1827. Min Act: -0.0001
Data Index: 659384 (C4 (Web Text))
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #19