Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2966 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 1.6150. Min Range: -1.6150
Max Act: 1.6150. Min Act: -0.0001
Data Index: 1646123 (Python Code)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.6150. Min Range: -1.6150
Max Act: 1.5700. Min Act: -0.0001
Data Index: 1554133 (Python Code)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.6150. Min Range: -1.6150
Max Act: 1.5711. Min Act: -0.0001
Data Index: 1446978 (Python Code)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.6150. Min Range: -1.6150
Max Act: 1.4387. Min Act: -0.0001
Data Index: 1511036 (Python Code)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.6150. Min Range: -1.6150
Max Act: 1.4604. Min Act: -0.0001
Data Index: 1376272 (Python Code)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.6150. Min Range: -1.6150
Max Act: 1.4581. Min Act: -0.0001
Data Index: 1547257 (Python Code)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.6150. Min Range: -1.6150
Max Act: 1.5565. Min Act: -0.0001
Data Index: 1633709 (Python Code)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.6150. Min Range: -1.6150
Max Act: 1.4320. Min Act: -0.0001
Data Index: 1595508 (Python Code)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.6150. Min Range: -1.6150
Max Act: 1.4246. Min Act: -0.0001
Data Index: 1612817 (Python Code)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.6150. Min Range: -1.6150
Max Act: 1.4210. Min Act: -0.0001
Data Index: 1515832 (Python Code)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.6150. Min Range: -1.6150
Max Act: 1.3645. Min Act: -0.0001
Data Index: 1371706 (Python Code)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.6150. Min Range: -1.6150
Max Act: 1.3832. Min Act: -0.0001
Data Index: 1645581 (Python Code)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.6150. Min Range: -1.6150
Max Act: 1.4607. Min Act: -0.0001
Data Index: 1497898 (Python Code)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.6150. Min Range: -1.6150
Max Act: 1.4729. Min Act: -0.0001
Data Index: 1461301 (Python Code)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.6150. Min Range: -1.6150
Max Act: 1.3948. Min Act: -0.0001
Data Index: 1589255 (Python Code)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.6150. Min Range: -1.6150
Max Act: 1.3879. Min Act: -0.0001
Data Index: 1584378 (Python Code)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.6150. Min Range: -1.6150
Max Act: 1.3252. Min Act: -0.0001
Data Index: 1440783 (Python Code)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.6150. Min Range: -1.6150
Max Act: 1.3308. Min Act: -0.0001
Data Index: 1655195 (Python Code)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.6150. Min Range: -1.6150
Max Act: 1.3784. Min Act: -0.0001
Data Index: 1513844 (Python Code)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.6150. Min Range: -1.6150
Max Act: 1.2929. Min Act: -0.0001
Data Index: 1576827 (Python Code)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #19