Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: The Pile
Neuron 1912 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')
Text #0
Max Range: 4.0234. Min Range: -4.0234
Max Act: 4.0234. Min Act: -0.0000
Data Index: 140547 (The Pile)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0234. Min Range: -4.0234
Max Act: 2.9922. Min Act: -0.0000
Data Index: 584910 (The Pile)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0234. Min Range: -4.0234
Max Act: 2.8767. Min Act: -0.0001
Data Index: 1987682 (The Pile)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0234. Min Range: -4.0234
Max Act: 2.6838. Min Act: -0.0000
Data Index: 202456 (The Pile)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0234. Min Range: -4.0234
Max Act: 2.4424. Min Act: -0.0000
Data Index: 152113 (The Pile)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0234. Min Range: -4.0234
Max Act: 2.2008. Min Act: -0.0000
Data Index: 1181867 (The Pile)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0234. Min Range: -4.0234
Max Act: 2.1489. Min Act: -0.0000
Data Index: 1886500 (The Pile)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0234. Min Range: -4.0234
Max Act: 2.0255. Min Act: -0.0000
Data Index: 680426 (The Pile)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0234. Min Range: -4.0234
Max Act: 1.9993. Min Act: -0.0000
Data Index: 195069 (The Pile)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0234. Min Range: -4.0234
Max Act: 1.5953. Min Act: -0.0000
Data Index: 1215850 (The Pile)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0234. Min Range: -4.0234
Max Act: 1.7743. Min Act: -0.0000
Data Index: 179736 (The Pile)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0234. Min Range: -4.0234
Max Act: 2.0248. Min Act: -0.0000
Data Index: 1210386 (The Pile)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0234. Min Range: -4.0234
Max Act: 1.9237. Min Act: -0.0000
Data Index: 1504617 (The Pile)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0234. Min Range: -4.0234
Max Act: 1.9420. Min Act: -0.0000
Data Index: 191035 (The Pile)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0234. Min Range: -4.0234
Max Act: 1.2880. Min Act: -0.0000
Data Index: 174825 (The Pile)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0234. Min Range: -4.0234
Max Act: 1.8936. Min Act: -0.0000
Data Index: 1910842 (The Pile)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0234. Min Range: -4.0234
Max Act: 1.9308. Min Act: -0.0000
Data Index: 1862568 (The Pile)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0234. Min Range: -4.0234
Max Act: 2.0955. Min Act: -0.0000
Data Index: 235748 (The Pile)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0234. Min Range: -4.0234
Max Act: 1.6950. Min Act: -0.0000
Data Index: 932202 (The Pile)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0234. Min Range: -4.0234
Max Act: 1.7023. Min Act: -0.0000
Data Index: 337647 (The Pile)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #19