Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3794 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 0.2421. Min Range: -0.2421
Max Act: 0.2421. Min Act: -0.0001
Data Index: 1591120 (Python Code)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.2421. Min Range: -0.2421
Max Act: 0.2308. Min Act: -0.0001
Data Index: 1456556 (Python Code)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.2421. Min Range: -0.2421
Max Act: 0.2343. Min Act: -0.0001
Data Index: 1370739 (Python Code)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.2421. Min Range: -0.2421
Max Act: 0.2015. Min Act: -0.0001
Data Index: 1362534 (Python Code)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.2421. Min Range: -0.2421
Max Act: 0.1888. Min Act: -0.0001
Data Index: 1432887 (Python Code)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.2421. Min Range: -0.2421
Max Act: 0.1877. Min Act: -0.0001
Data Index: 1393014 (Python Code)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.2421. Min Range: -0.2421
Max Act: 0.1821. Min Act: -0.0001
Data Index: 1400174 (Python Code)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.2421. Min Range: -0.2421
Max Act: 0.1790. Min Act: -0.0001
Data Index: 1655510 (Python Code)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.2421. Min Range: -0.2421
Max Act: 0.1774. Min Act: -0.0001
Data Index: 1455121 (Python Code)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.2421. Min Range: -0.2421
Max Act: 0.1814. Min Act: -0.0001
Data Index: 1628569 (Python Code)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.2421. Min Range: -0.2421
Max Act: 0.1726. Min Act: -0.0001
Data Index: 1465902 (Python Code)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.2421. Min Range: -0.2421
Max Act: 0.1727. Min Act: -0.0001
Data Index: 1577234 (Python Code)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.2421. Min Range: -0.2421
Max Act: 0.1686. Min Act: -0.0001
Data Index: 1400665 (Python Code)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.2421. Min Range: -0.2421
Max Act: 0.1770. Min Act: -0.0001
Data Index: 1537242 (Python Code)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.2421. Min Range: -0.2421
Max Act: 0.1735. Min Act: -0.0001
Data Index: 1370256 (Python Code)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.2421. Min Range: -0.2421
Max Act: 0.1700. Min Act: -0.0001
Data Index: 1563365 (Python Code)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.2421. Min Range: -0.2421
Max Act: 0.1692. Min Act: -0.0001
Data Index: 1435723 (Python Code)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.2421. Min Range: -0.2421
Max Act: 0.1580. Min Act: -0.0001
Data Index: 1533513 (Python Code)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.2421. Min Range: -0.2421
Max Act: 0.1575. Min Act: -0.0001
Data Index: 1416272 (Python Code)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.2421. Min Range: -0.2421
Max Act: 0.1591. Min Act: -0.0001
Data Index: 1500759 (Python Code)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #19