Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 4076 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 1.4825. Min Range: -1.4825
Max Act: 1.4825. Min Act: -0.0001
Data Index: 1562161 (Python Code)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.4825. Min Range: -1.4825
Max Act: 1.3856. Min Act: -0.0001
Data Index: 1388989 (Python Code)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.4825. Min Range: -1.4825
Max Act: 1.2744. Min Act: -0.0001
Data Index: 1649236 (Python Code)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.4825. Min Range: -1.4825
Max Act: 1.1990. Min Act: -0.0001
Data Index: 1642614 (Python Code)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.4825. Min Range: -1.4825
Max Act: 1.1887. Min Act: -0.0001
Data Index: 1591029 (Python Code)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.4825. Min Range: -1.4825
Max Act: 1.2230. Min Act: -0.0001
Data Index: 1386116 (Python Code)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.4825. Min Range: -1.4825
Max Act: 1.2961. Min Act: -0.0001
Data Index: 1430416 (Python Code)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.4825. Min Range: -1.4825
Max Act: 1.2918. Min Act: -0.0001
Data Index: 1606140 (Python Code)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.4825. Min Range: -1.4825
Max Act: 1.2108. Min Act: -0.0001
Data Index: 1520610 (Python Code)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.4825. Min Range: -1.4825
Max Act: 1.1704. Min Act: -0.0001
Data Index: 1475869 (Python Code)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.4825. Min Range: -1.4825
Max Act: 1.1764. Min Act: -0.0001
Data Index: 1507849 (Python Code)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.4825. Min Range: -1.4825
Max Act: 1.2007. Min Act: -0.0001
Data Index: 1415024 (Python Code)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.4825. Min Range: -1.4825
Max Act: 1.1255. Min Act: -0.0001
Data Index: 1558292 (Python Code)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.4825. Min Range: -1.4825
Max Act: 1.2007. Min Act: -0.0001
Data Index: 1542537 (Python Code)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.4825. Min Range: -1.4825
Max Act: 1.1736. Min Act: -0.0001
Data Index: 1465391 (Python Code)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.4825. Min Range: -1.4825
Max Act: 1.1601. Min Act: -0.0001
Data Index: 1444022 (Python Code)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.4825. Min Range: -1.4825
Max Act: 1.1153. Min Act: -0.0001
Data Index: 1366507 (Python Code)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.4825. Min Range: -1.4825
Max Act: 1.0716. Min Act: -0.0001
Data Index: 1520320 (Python Code)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.4825. Min Range: -1.4825
Max Act: 1.0658. Min Act: -0.0001
Data Index: 1362807 (Python Code)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.4825. Min Range: -1.4825
Max Act: 1.0842. Min Act: -0.0001
Data Index: 1638702 (Python Code)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #19