Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 58 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 1.2229. Min Range: -1.2229
Max Act: 1.2229. Min Act: -0.0001
Data Index: 1578528 (Python Code)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.2229. Min Range: -1.2229
Max Act: 1.1618. Min Act: -0.0001
Data Index: 1410193 (Python Code)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.2229. Min Range: -1.2229
Max Act: 1.0871. Min Act: -0.0001
Data Index: 24156 (C4 (Web Text))
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.2229. Min Range: -1.2229
Max Act: 1.1185. Min Act: -0.0001
Data Index: 1482962 (Python Code)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.2229. Min Range: -1.2229
Max Act: 1.0866. Min Act: -0.0001
Data Index: 1457733 (Python Code)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.2229. Min Range: -1.2229
Max Act: 1.0596. Min Act: -0.0001
Data Index: 1444600 (Python Code)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.2229. Min Range: -1.2229
Max Act: 1.0058. Min Act: -0.0001
Data Index: 1263162 (C4 (Web Text))
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.2229. Min Range: -1.2229
Max Act: 1.0534. Min Act: -0.0001
Data Index: 1647194 (Python Code)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.2229. Min Range: -1.2229
Max Act: 0.9752. Min Act: -0.0001
Data Index: 815215 (C4 (Web Text))
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.2229. Min Range: -1.2229
Max Act: 0.9803. Min Act: -0.0001
Data Index: 139524 (C4 (Web Text))
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.2229. Min Range: -1.2229
Max Act: 0.9795. Min Act: -0.0001
Data Index: 1408428 (Python Code)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.2229. Min Range: -1.2229
Max Act: 0.9860. Min Act: -0.0001
Data Index: 1427374 (Python Code)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.2229. Min Range: -1.2229
Max Act: 0.9750. Min Act: -0.0001
Data Index: 1383801 (Python Code)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.2229. Min Range: -1.2229
Max Act: 0.9500. Min Act: -0.0001
Data Index: 1511769 (Python Code)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.2229. Min Range: -1.2229
Max Act: 1.1013. Min Act: -0.0001
Data Index: 509179 (C4 (Web Text))
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.2229. Min Range: -1.2229
Max Act: 0.9376. Min Act: -0.0001
Data Index: 737452 (C4 (Web Text))
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.2229. Min Range: -1.2229
Max Act: 0.9460. Min Act: -0.0001
Data Index: 1606561 (Python Code)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.2229. Min Range: -1.2229
Max Act: 0.9913. Min Act: -0.0001
Data Index: 1499986 (Python Code)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.2229. Min Range: -1.2229
Max Act: 0.9314. Min Act: -0.0001
Data Index: 1481074 (Python Code)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.2229. Min Range: -1.2229
Max Act: 0.8332. Min Act: -0.0001
Data Index: 330393 (C4 (Web Text))
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #19