Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 360 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 1.8242. Min Range: -1.8242
Max Act: 1.8242. Min Act: -0.0001
Data Index: 1442981 (Python Code)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.8242. Min Range: -1.8242
Max Act: 1.7300. Min Act: -0.0001
Data Index: 1628343 (Python Code)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.8242. Min Range: -1.8242
Max Act: 1.5966. Min Act: -0.0001
Data Index: 1365238 (Python Code)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.8242. Min Range: -1.8242
Max Act: 1.5518. Min Act: -0.0001
Data Index: 1650692 (Python Code)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.8242. Min Range: -1.8242
Max Act: 1.7610. Min Act: -0.0001
Data Index: 1557243 (Python Code)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.8242. Min Range: -1.8242
Max Act: 1.7999. Min Act: -0.0001
Data Index: 1374021 (Python Code)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.8242. Min Range: -1.8242
Max Act: 1.6272. Min Act: -0.0001
Data Index: 1497400 (Python Code)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.8242. Min Range: -1.8242
Max Act: 1.5729. Min Act: -0.0001
Data Index: 1529816 (Python Code)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.8242. Min Range: -1.8242
Max Act: 1.5653. Min Act: -0.0001
Data Index: 1362583 (Python Code)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.8242. Min Range: -1.8242
Max Act: 1.4945. Min Act: -0.0001
Data Index: 1521865 (Python Code)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.8242. Min Range: -1.8242
Max Act: 1.4247. Min Act: -0.0001
Data Index: 1432989 (Python Code)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.8242. Min Range: -1.8242
Max Act: 1.6510. Min Act: -0.0001
Data Index: 1398167 (Python Code)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.8242. Min Range: -1.8242
Max Act: 1.5547. Min Act: -0.0001
Data Index: 1567075 (Python Code)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.8242. Min Range: -1.8242
Max Act: 1.5110. Min Act: -0.0001
Data Index: 1498170 (Python Code)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.8242. Min Range: -1.8242
Max Act: 1.6760. Min Act: -0.0001
Data Index: 1600738 (Python Code)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.8242. Min Range: -1.8242
Max Act: 1.5171. Min Act: -0.0001
Data Index: 1424006 (Python Code)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.8242. Min Range: -1.8242
Max Act: 1.4903. Min Act: -0.0001
Data Index: 1371813 (Python Code)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.8242. Min Range: -1.8242
Max Act: 1.4925. Min Act: -0.0001
Data Index: 1608703 (Python Code)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.8242. Min Range: -1.8242
Max Act: 1.5136. Min Act: -0.0001
Data Index: 1572567 (Python Code)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.8242. Min Range: -1.8242
Max Act: 1.5104. Min Act: -0.0001
Data Index: 1618928 (Python Code)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #19