Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 4372 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 2.8753. Min Range: -2.8753
Max Act: 2.8753. Min Act: -0.0001
Data Index: 1406870 (Python Code)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8753. Min Range: -2.8753
Max Act: 2.3668. Min Act: -0.0001
Data Index: 1517224 (Python Code)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8753. Min Range: -2.8753
Max Act: 2.4889. Min Act: -0.0001
Data Index: 1361844 (Python Code)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8753. Min Range: -2.8753
Max Act: 2.2798. Min Act: -0.0001
Data Index: 1545137 (Python Code)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8753. Min Range: -2.8753
Max Act: 2.3222. Min Act: -0.0001
Data Index: 1388951 (Python Code)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8753. Min Range: -2.8753
Max Act: 2.0650. Min Act: -0.0001
Data Index: 1409435 (Python Code)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8753. Min Range: -2.8753
Max Act: 2.1158. Min Act: -0.0001
Data Index: 1561725 (Python Code)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8753. Min Range: -2.8753
Max Act: 2.0407. Min Act: -0.0001
Data Index: 1528247 (Python Code)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8753. Min Range: -2.8753
Max Act: 2.0576. Min Act: -0.0001
Data Index: 1469313 (Python Code)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8753. Min Range: -2.8753
Max Act: 1.9833. Min Act: -0.0001
Data Index: 1432326 (Python Code)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8753. Min Range: -2.8753
Max Act: 2.0163. Min Act: -0.0001
Data Index: 1364854 (Python Code)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8753. Min Range: -2.8753
Max Act: 1.9142. Min Act: -0.0001
Data Index: 1646703 (Python Code)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8753. Min Range: -2.8753
Max Act: 2.0264. Min Act: -0.0001
Data Index: 1577321 (Python Code)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8753. Min Range: -2.8753
Max Act: 1.9025. Min Act: -0.0001
Data Index: 1416787 (Python Code)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8753. Min Range: -2.8753
Max Act: 1.9939. Min Act: -0.0001
Data Index: 1622194 (Python Code)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8753. Min Range: -2.8753
Max Act: 1.8850. Min Act: -0.0001
Data Index: 1644719 (Python Code)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8753. Min Range: -2.8753
Max Act: 1.8834. Min Act: -0.0001
Data Index: 1575325 (Python Code)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8753. Min Range: -2.8753
Max Act: 1.8723. Min Act: -0.0001
Data Index: 1590895 (Python Code)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8753. Min Range: -2.8753
Max Act: 1.8102. Min Act: -0.0001
Data Index: 1602002 (Python Code)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8753. Min Range: -2.8753
Max Act: 1.8443. Min Act: -0.0001
Data Index: 1640382 (Python Code)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #19