Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2852 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 0.1836. Min Range: -0.1836
Max Act: 0.1836. Min Act: -0.0003
Data Index: 1366223 (Python Code)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.1836. Min Range: -0.1836
Max Act: 0.1739. Min Act: -0.0004
Data Index: 1533356 (Python Code)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.1836. Min Range: -0.1836
Max Act: 0.1596. Min Act: -0.0003
Data Index: 136745 (C4 (Web Text))
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.1836. Min Range: -0.1836
Max Act: 0.1649. Min Act: -0.0003
Data Index: 1558566 (Python Code)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.1836. Min Range: -0.1836
Max Act: 0.1597. Min Act: -0.0003
Data Index: 1625404 (Python Code)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.1836. Min Range: -0.1836
Max Act: 0.1581. Min Act: -0.0003
Data Index: 1417060 (Python Code)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.1836. Min Range: -0.1836
Max Act: 0.1452. Min Act: -0.0003
Data Index: 1529425 (Python Code)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.1836. Min Range: -0.1836
Max Act: 0.1684. Min Act: -0.0003
Data Index: 1599923 (Python Code)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.1836. Min Range: -0.1836
Max Act: 0.1527. Min Act: -0.0003
Data Index: 1423348 (Python Code)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.1836. Min Range: -0.1836
Max Act: 0.1400. Min Act: -0.0003
Data Index: 1470989 (Python Code)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.1836. Min Range: -0.1836
Max Act: 0.1605. Min Act: -0.0003
Data Index: 1620268 (Python Code)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.1836. Min Range: -0.1836
Max Act: 0.1640. Min Act: -0.0003
Data Index: 1372862 (Python Code)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.1836. Min Range: -0.1836
Max Act: 0.1382. Min Act: -0.0003
Data Index: 1391292 (Python Code)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.1836. Min Range: -0.1836
Max Act: 0.1746. Min Act: -0.0003
Data Index: 1451090 (Python Code)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.1836. Min Range: -0.1836
Max Act: 0.1618. Min Act: -0.0003
Data Index: 1462301 (Python Code)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.1836. Min Range: -0.1836
Max Act: 0.1620. Min Act: -0.0003
Data Index: 1655392 (Python Code)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.1836. Min Range: -0.1836
Max Act: 0.1314. Min Act: -0.0003
Data Index: 1565974 (Python Code)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.1836. Min Range: -0.1836
Max Act: 0.1302. Min Act: -0.0003
Data Index: 1456601 (Python Code)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.1836. Min Range: -0.1836
Max Act: 0.1347. Min Act: -0.0003
Data Index: 1656227 (Python Code)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.1836. Min Range: -0.1836
Max Act: 0.1653. Min Act: -0.0003
Data Index: 1374263 (Python Code)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #19