Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3232 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 1.2009. Min Range: -1.2009
Max Act: 1.0438. Min Act: -0.0001
Data Index: 916197 (C4 (Web Text))
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.2009. Min Range: -1.2009
Max Act: 1.2009. Min Act: -0.0001
Data Index: 1368798 (Python Code)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.2009. Min Range: -1.2009
Max Act: 1.1424. Min Act: -0.0001
Data Index: 1364237 (Python Code)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.2009. Min Range: -1.2009
Max Act: 1.1964. Min Act: -0.0001
Data Index: 1499615 (Python Code)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.2009. Min Range: -1.2009
Max Act: 0.9524. Min Act: -0.0001
Data Index: 6761 (C4 (Web Text))
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.2009. Min Range: -1.2009
Max Act: 1.1655. Min Act: -0.0001
Data Index: 37182 (C4 (Web Text))
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.2009. Min Range: -1.2009
Max Act: 1.0661. Min Act: -0.0001
Data Index: 1391682 (Python Code)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.2009. Min Range: -1.2009
Max Act: 1.0616. Min Act: -0.0001
Data Index: 1562797 (Python Code)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.2009. Min Range: -1.2009
Max Act: 1.1695. Min Act: -0.0001
Data Index: 86676 (C4 (Web Text))
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.2009. Min Range: -1.2009
Max Act: 1.0992. Min Act: -0.0001
Data Index: 1646392 (Python Code)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.2009. Min Range: -1.2009
Max Act: 1.0611. Min Act: -0.0001
Data Index: 240834 (C4 (Web Text))
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.2009. Min Range: -1.2009
Max Act: 1.0216. Min Act: -0.0001
Data Index: 1655058 (Python Code)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.2009. Min Range: -1.2009
Max Act: 1.0116. Min Act: -0.0001
Data Index: 1499491 (Python Code)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.2009. Min Range: -1.2009
Max Act: 1.0910. Min Act: -0.0001
Data Index: 445031 (C4 (Web Text))
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.2009. Min Range: -1.2009
Max Act: 1.0261. Min Act: -0.0001
Data Index: 868397 (C4 (Web Text))
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.2009. Min Range: -1.2009
Max Act: 1.0616. Min Act: -0.0001
Data Index: 703993 (C4 (Web Text))
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.2009. Min Range: -1.2009
Max Act: 0.9901. Min Act: -0.0001
Data Index: 1434513 (Python Code)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.2009. Min Range: -1.2009
Max Act: 1.0383. Min Act: -0.0001
Data Index: 1385339 (Python Code)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.2009. Min Range: -1.2009
Max Act: 0.9240. Min Act: -0.0001
Data Index: 498126 (C4 (Web Text))
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.2009. Min Range: -1.2009
Max Act: 1.0394. Min Act: -0.0001
Data Index: 1231808 (C4 (Web Text))
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #19