Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2801 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 0.1857. Min Range: -0.1857
Max Act: 0.1857. Min Act: -0.0001
Data Index: 1611506 (Python Code)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.1857. Min Range: -0.1857
Max Act: 0.1839. Min Act: -0.0001
Data Index: 864815 (C4 (Web Text))
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.1857. Min Range: -0.1857
Max Act: 0.1824. Min Act: -0.0001
Data Index: 1155016 (C4 (Web Text))
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.1857. Min Range: -0.1857
Max Act: 0.1853. Min Act: -0.0001
Data Index: 1589334 (Python Code)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.1857. Min Range: -0.1857
Max Act: 0.1715. Min Act: -0.0001
Data Index: 1616426 (Python Code)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.1857. Min Range: -0.1857
Max Act: 0.1770. Min Act: -0.0001
Data Index: 1532477 (Python Code)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.1857. Min Range: -0.1857
Max Act: 0.1626. Min Act: -0.0001
Data Index: 333509 (C4 (Web Text))
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.1857. Min Range: -0.1857
Max Act: 0.1590. Min Act: -0.0001
Data Index: 992088 (C4 (Web Text))
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.1857. Min Range: -0.1857
Max Act: 0.1531. Min Act: -0.0001
Data Index: 105558 (C4 (Web Text))
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.1857. Min Range: -0.1857
Max Act: 0.1701. Min Act: -0.0001
Data Index: 1389035 (Python Code)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.1857. Min Range: -0.1857
Max Act: 0.1476. Min Act: -0.0001
Data Index: 66072 (C4 (Web Text))
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.1857. Min Range: -0.1857
Max Act: 0.1682. Min Act: -0.0001
Data Index: 978034 (C4 (Web Text))
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.1857. Min Range: -0.1857
Max Act: 0.1501. Min Act: -0.0001
Data Index: 1608805 (Python Code)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.1857. Min Range: -0.1857
Max Act: 0.1539. Min Act: -0.0001
Data Index: 885304 (C4 (Web Text))
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.1857. Min Range: -0.1857
Max Act: 0.1486. Min Act: -0.0001
Data Index: 90159 (C4 (Web Text))
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.1857. Min Range: -0.1857
Max Act: 0.1381. Min Act: -0.0001
Data Index: 1265808 (C4 (Web Text))
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.1857. Min Range: -0.1857
Max Act: 0.1548. Min Act: -0.0001
Data Index: 60864 (C4 (Web Text))
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.1857. Min Range: -0.1857
Max Act: 0.1481. Min Act: -0.0001
Data Index: 11173 (C4 (Web Text))
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.1857. Min Range: -0.1857
Max Act: 0.1427. Min Act: -0.0001
Data Index: 1354259 (C4 (Web Text))
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.1857. Min Range: -0.1857
Max Act: 0.1322. Min Act: -0.0001
Data Index: 205230 (C4 (Web Text))
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #19