Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: The Pile
Neuron 2423 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')
Text #0
Max Range: 1.1363. Min Range: -1.1363
Max Act: 1.1363. Min Act: -0.0003
Data Index: 655434 (The Pile)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.1363. Min Range: -1.1363
Max Act: 1.1186. Min Act: -0.0003
Data Index: 1618405 (The Pile)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.1363. Min Range: -1.1363
Max Act: 1.1029. Min Act: -0.0003
Data Index: 1728189 (The Pile)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.1363. Min Range: -1.1363
Max Act: 1.0994. Min Act: -0.0003
Data Index: 928625 (The Pile)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.1363. Min Range: -1.1363
Max Act: 1.0904. Min Act: -0.0003
Data Index: 1215260 (The Pile)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.1363. Min Range: -1.1363
Max Act: 1.0639. Min Act: -0.0003
Data Index: 1695790 (The Pile)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.1363. Min Range: -1.1363
Max Act: 1.0811. Min Act: -0.0003
Data Index: 1339555 (The Pile)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.1363. Min Range: -1.1363
Max Act: 1.0481. Min Act: -0.0003
Data Index: 351588 (The Pile)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.1363. Min Range: -1.1363
Max Act: 1.0620. Min Act: -0.0003
Data Index: 1576053 (The Pile)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.1363. Min Range: -1.1363
Max Act: 1.0137. Min Act: -0.0003
Data Index: 1096787 (The Pile)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.1363. Min Range: -1.1363
Max Act: 1.0122. Min Act: -0.0003
Data Index: 952875 (The Pile)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.1363. Min Range: -1.1363
Max Act: 1.0658. Min Act: -0.0003
Data Index: 1376501 (The Pile)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.1363. Min Range: -1.1363
Max Act: 1.0045. Min Act: -0.0003
Data Index: 487744 (The Pile)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.1363. Min Range: -1.1363
Max Act: 1.0265. Min Act: -0.0003
Data Index: 1978981 (The Pile)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.1363. Min Range: -1.1363
Max Act: 1.0169. Min Act: -0.0003
Data Index: 1454954 (The Pile)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.1363. Min Range: -1.1363
Max Act: 1.0425. Min Act: -0.0003
Data Index: 856707 (The Pile)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.1363. Min Range: -1.1363
Max Act: 1.0121. Min Act: -0.0003
Data Index: 1044106 (The Pile)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.1363. Min Range: -1.1363
Max Act: 0.9804. Min Act: -0.0003
Data Index: 1099199 (The Pile)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.1363. Min Range: -1.1363
Max Act: 1.0040. Min Act: -0.0003
Data Index: 533444 (The Pile)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.1363. Min Range: -1.1363
Max Act: 1.0304. Min Act: -0.0003
Data Index: 468546 (The Pile)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #19