Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2351 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 1.9057. Min Range: -1.9057
Max Act: 1.7075. Min Act: -0.0001
Data Index: 1523832 (Python Code)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.9057. Min Range: -1.9057
Max Act: 1.8786. Min Act: -0.0001
Data Index: 1485634 (Python Code)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.9057. Min Range: -1.9057
Max Act: 1.7775. Min Act: -0.0001
Data Index: 1623018 (Python Code)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.9057. Min Range: -1.9057
Max Act: 1.9057. Min Act: -0.0001
Data Index: 1381218 (Python Code)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.9057. Min Range: -1.9057
Max Act: 1.8013. Min Act: -0.0001
Data Index: 1451129 (Python Code)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.9057. Min Range: -1.9057
Max Act: 1.7018. Min Act: -0.0001
Data Index: 1569649 (Python Code)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.9057. Min Range: -1.9057
Max Act: 1.7208. Min Act: -0.0001
Data Index: 1603316 (Python Code)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.9057. Min Range: -1.9057
Max Act: 1.6585. Min Act: -0.0001
Data Index: 1613626 (Python Code)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.9057. Min Range: -1.9057
Max Act: 1.7481. Min Act: -0.0001
Data Index: 1522829 (Python Code)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.9057. Min Range: -1.9057
Max Act: 1.6747. Min Act: -0.0001
Data Index: 1577819 (Python Code)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.9057. Min Range: -1.9057
Max Act: 1.6585. Min Act: -0.0001
Data Index: 1563969 (Python Code)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.9057. Min Range: -1.9057
Max Act: 1.6526. Min Act: -0.0001
Data Index: 1568523 (Python Code)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.9057. Min Range: -1.9057
Max Act: 1.6620. Min Act: -0.0001
Data Index: 1635422 (Python Code)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.9057. Min Range: -1.9057
Max Act: 1.6406. Min Act: -0.0001
Data Index: 1407830 (Python Code)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.9057. Min Range: -1.9057
Max Act: 1.6309. Min Act: -0.0001
Data Index: 1449185 (Python Code)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.9057. Min Range: -1.9057
Max Act: 1.7160. Min Act: -0.0001
Data Index: 1370223 (Python Code)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.9057. Min Range: -1.9057
Max Act: 1.6729. Min Act: -0.0001
Data Index: 1641392 (Python Code)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.9057. Min Range: -1.9057
Max Act: 1.5637. Min Act: -0.0001
Data Index: 1393566 (Python Code)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.9057. Min Range: -1.9057
Max Act: 1.6421. Min Act: -0.0001
Data Index: 1608327 (Python Code)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.9057. Min Range: -1.9057
Max Act: 1.6003. Min Act: -0.0001
Data Index: 1404820 (Python Code)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #19