Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2883 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 0.2441. Min Range: -0.2441
Max Act: 0.2441. Min Act: -0.0001
Data Index: 1544631 (Python Code)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.2441. Min Range: -0.2441
Max Act: 0.1999. Min Act: -0.0001
Data Index: 1480069 (Python Code)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.2441. Min Range: -0.2441
Max Act: 0.2221. Min Act: -0.0001
Data Index: 1559870 (Python Code)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.2441. Min Range: -0.2441
Max Act: 0.2115. Min Act: -0.0001
Data Index: 1516587 (Python Code)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.2441. Min Range: -0.2441
Max Act: 0.2088. Min Act: -0.0001
Data Index: 1553553 (Python Code)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.2441. Min Range: -0.2441
Max Act: 0.1927. Min Act: -0.0001
Data Index: 1450176 (Python Code)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.2441. Min Range: -0.2441
Max Act: 0.1995. Min Act: -0.0001
Data Index: 1364329 (Python Code)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.2441. Min Range: -0.2441
Max Act: 0.1918. Min Act: -0.0001
Data Index: 1581445 (Python Code)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.2441. Min Range: -0.2441
Max Act: 0.1895. Min Act: -0.0001
Data Index: 1490977 (Python Code)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.2441. Min Range: -0.2441
Max Act: 0.2020. Min Act: -0.0001
Data Index: 1478234 (Python Code)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.2441. Min Range: -0.2441
Max Act: 0.1996. Min Act: -0.0001
Data Index: 1541351 (Python Code)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.2441. Min Range: -0.2441
Max Act: 0.1998. Min Act: -0.0001
Data Index: 1373190 (Python Code)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.2441. Min Range: -0.2441
Max Act: 0.1890. Min Act: -0.0001
Data Index: 1646579 (Python Code)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.2441. Min Range: -0.2441
Max Act: 0.1858. Min Act: -0.0001
Data Index: 1463305 (Python Code)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.2441. Min Range: -0.2441
Max Act: 0.1913. Min Act: -0.0001
Data Index: 1603537 (Python Code)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.2441. Min Range: -0.2441
Max Act: 0.1920. Min Act: -0.0001
Data Index: 1367046 (Python Code)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.2441. Min Range: -0.2441
Max Act: 0.1769. Min Act: -0.0001
Data Index: 1466770 (Python Code)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.2441. Min Range: -0.2441
Max Act: 0.1900. Min Act: -0.0001
Data Index: 1597484 (Python Code)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.2441. Min Range: -0.2441
Max Act: 0.1901. Min Act: -0.0001
Data Index: 1534063 (Python Code)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.2441. Min Range: -0.2441
Max Act: 0.1873. Min Act: -0.0001
Data Index: 1656563 (Python Code)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #19