Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1687 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 3.5211. Min Range: -3.5211
Max Act: 3.5211. Min Act: -0.0001
Data Index: 1630637 (Python Code)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5211. Min Range: -3.5211
Max Act: 3.0006. Min Act: -0.0001
Data Index: 1318465 (C4 (Web Text))
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5211. Min Range: -3.5211
Max Act: 2.8419. Min Act: -0.0001
Data Index: 1182540 (C4 (Web Text))
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5211. Min Range: -3.5211
Max Act: 2.9511. Min Act: -0.0001
Data Index: 1252208 (C4 (Web Text))
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5211. Min Range: -3.5211
Max Act: 3.0343. Min Act: -0.0001
Data Index: 1350012 (C4 (Web Text))
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5211. Min Range: -3.5211
Max Act: 2.8602. Min Act: -0.0001
Data Index: 1341274 (C4 (Web Text))
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5211. Min Range: -3.5211
Max Act: 2.8251. Min Act: -0.0001
Data Index: 1448977 (Python Code)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5211. Min Range: -3.5211
Max Act: 2.9248. Min Act: -0.0001
Data Index: 202641 (C4 (Web Text))
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5211. Min Range: -3.5211
Max Act: 2.7886. Min Act: -0.0001
Data Index: 1378959 (Python Code)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5211. Min Range: -3.5211
Max Act: 2.8629. Min Act: -0.0001
Data Index: 1089136 (C4 (Web Text))
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5211. Min Range: -3.5211
Max Act: 2.8596. Min Act: -0.0001
Data Index: 1097720 (C4 (Web Text))
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5211. Min Range: -3.5211
Max Act: 2.5842. Min Act: -0.0001
Data Index: 174416 (C4 (Web Text))
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5211. Min Range: -3.5211
Max Act: 2.6953. Min Act: -0.0001
Data Index: 105533 (C4 (Web Text))
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5211. Min Range: -3.5211
Max Act: 2.8103. Min Act: -0.0001
Data Index: 1143530 (C4 (Web Text))
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5211. Min Range: -3.5211
Max Act: 2.5928. Min Act: -0.0001
Data Index: 1193696 (C4 (Web Text))
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5211. Min Range: -3.5211
Max Act: 2.5732. Min Act: -0.0001
Data Index: 209333 (C4 (Web Text))
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5211. Min Range: -3.5211
Max Act: 2.5583. Min Act: -0.0001
Data Index: 643024 (C4 (Web Text))
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5211. Min Range: -3.5211
Max Act: 2.3989. Min Act: -0.0001
Data Index: 265183 (C4 (Web Text))
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5211. Min Range: -3.5211
Max Act: 2.3962. Min Act: -0.0001
Data Index: 1486409 (Python Code)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5211. Min Range: -3.5211
Max Act: 2.5281. Min Act: -0.0001
Data Index: 1402727 (Python Code)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #19