Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2946 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 6.2422. Min Range: -6.2422
Max Act: 6.2422. Min Act: -0.0001
Data Index: 1464463 (Python Code)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2422. Min Range: -6.2422
Max Act: 6.1522. Min Act: -0.0001
Data Index: 1499900 (Python Code)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2422. Min Range: -6.2422
Max Act: 5.7586. Min Act: -0.0001
Data Index: 1550876 (Python Code)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2422. Min Range: -6.2422
Max Act: 5.3783. Min Act: -0.0001
Data Index: 1443747 (Python Code)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2422. Min Range: -6.2422
Max Act: 5.7266. Min Act: -0.0001
Data Index: 1577843 (Python Code)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2422. Min Range: -6.2422
Max Act: 5.5290. Min Act: -0.0001
Data Index: 1531952 (Python Code)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2422. Min Range: -6.2422
Max Act: 5.6578. Min Act: -0.0001
Data Index: 1431808 (Python Code)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2422. Min Range: -6.2422
Max Act: 5.4487. Min Act: -0.0001
Data Index: 1375962 (Python Code)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2422. Min Range: -6.2422
Max Act: 5.6563. Min Act: -0.0001
Data Index: 1577563 (Python Code)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2422. Min Range: -6.2422
Max Act: 5.7823. Min Act: -0.0001
Data Index: 1554879 (Python Code)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2422. Min Range: -6.2422
Max Act: 5.6010. Min Act: -0.0001
Data Index: 1602318 (Python Code)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2422. Min Range: -6.2422
Max Act: 5.6188. Min Act: -0.0001
Data Index: 1609993 (Python Code)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2422. Min Range: -6.2422
Max Act: 5.7537. Min Act: -0.0001
Data Index: 1654207 (Python Code)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2422. Min Range: -6.2422
Max Act: 5.7076. Min Act: -0.0001
Data Index: 1407150 (Python Code)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2422. Min Range: -6.2422
Max Act: 5.1598. Min Act: -0.0001
Data Index: 1643818 (Python Code)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2422. Min Range: -6.2422
Max Act: 5.4826. Min Act: -0.0001
Data Index: 1561113 (Python Code)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2422. Min Range: -6.2422
Max Act: 5.4918. Min Act: -0.0001
Data Index: 1627851 (Python Code)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2422. Min Range: -6.2422
Max Act: 5.0990. Min Act: -0.0001
Data Index: 1545342 (Python Code)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2422. Min Range: -6.2422
Max Act: 5.2175. Min Act: -0.0001
Data Index: 1585604 (Python Code)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2422. Min Range: -6.2422
Max Act: 5.0226. Min Act: -0.0001
Data Index: 1379959 (Python Code)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #19