Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: The Pile
Neuron 716 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')
Text #0
Max Range: 0.4913. Min Range: -0.4913
Max Act: 0.4838. Min Act: -0.0001
Data Index: 1479837 (The Pile)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.4913. Min Range: -0.4913
Max Act: 0.4642. Min Act: -0.0001
Data Index: 1753847 (The Pile)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.4913. Min Range: -0.4913
Max Act: 0.4420. Min Act: -0.0001
Data Index: 339034 (The Pile)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.4913. Min Range: -0.4913
Max Act: 0.4913. Min Act: -0.0001
Data Index: 837411 (The Pile)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.4913. Min Range: -0.4913
Max Act: 0.4679. Min Act: -0.0001
Data Index: 362414 (The Pile)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.4913. Min Range: -0.4913
Max Act: 0.4204. Min Act: -0.0001
Data Index: 865586 (The Pile)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.4913. Min Range: -0.4913
Max Act: 0.4243. Min Act: -0.0001
Data Index: 1304778 (The Pile)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.4913. Min Range: -0.4913
Max Act: 0.4147. Min Act: -0.0001
Data Index: 1132508 (The Pile)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.4913. Min Range: -0.4913
Max Act: 0.3967. Min Act: -0.0001
Data Index: 684313 (The Pile)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.4913. Min Range: -0.4913
Max Act: 0.4415. Min Act: -0.0001
Data Index: 1571989 (The Pile)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.4913. Min Range: -0.4913
Max Act: 0.4264. Min Act: -0.0001
Data Index: 519130 (The Pile)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.4913. Min Range: -0.4913
Max Act: 0.4216. Min Act: -0.0001
Data Index: 1532543 (The Pile)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.4913. Min Range: -0.4913
Max Act: 0.4206. Min Act: -0.0001
Data Index: 1323778 (The Pile)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.4913. Min Range: -0.4913
Max Act: 0.4007. Min Act: -0.0001
Data Index: 139392 (The Pile)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.4913. Min Range: -0.4913
Max Act: 0.3809. Min Act: -0.0001
Data Index: 1750656 (The Pile)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.4913. Min Range: -0.4913
Max Act: 0.3712. Min Act: -0.0001
Data Index: 1191142 (The Pile)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.4913. Min Range: -0.4913
Max Act: 0.4047. Min Act: -0.0001
Data Index: 1516767 (The Pile)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.4913. Min Range: -0.4913
Max Act: 0.3775. Min Act: -0.0001
Data Index: 616840 (The Pile)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.4913. Min Range: -0.4913
Max Act: 0.4023. Min Act: -0.0001
Data Index: 575976 (The Pile)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.4913. Min Range: -0.4913
Max Act: 0.3970. Min Act: -0.0001
Data Index: 10313 (The Pile)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #19