Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2771 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 1.1790. Min Range: -1.1790
Max Act: 1.1790. Min Act: -0.0001
Data Index: 1458139 (Python Code)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.1790. Min Range: -1.1790
Max Act: 1.1338. Min Act: -0.0001
Data Index: 1548713 (Python Code)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.1790. Min Range: -1.1790
Max Act: 1.1187. Min Act: -0.0001
Data Index: 1402820 (Python Code)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.1790. Min Range: -1.1790
Max Act: 1.0871. Min Act: -0.0001
Data Index: 1529035 (Python Code)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.1790. Min Range: -1.1790
Max Act: 0.9984. Min Act: -0.0001
Data Index: 135664 (C4 (Web Text))
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.1790. Min Range: -1.1790
Max Act: 1.0130. Min Act: -0.0001
Data Index: 285534 (C4 (Web Text))
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.1790. Min Range: -1.1790
Max Act: 0.9904. Min Act: -0.0001
Data Index: 1422236 (Python Code)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.1790. Min Range: -1.1790
Max Act: 1.0007. Min Act: -0.0001
Data Index: 1435922 (Python Code)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.1790. Min Range: -1.1790
Max Act: 0.9974. Min Act: -0.0001
Data Index: 1401832 (Python Code)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.1790. Min Range: -1.1790
Max Act: 0.9949. Min Act: -0.0001
Data Index: 1422765 (Python Code)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.1790. Min Range: -1.1790
Max Act: 0.9882. Min Act: -0.0001
Data Index: 1409609 (Python Code)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.1790. Min Range: -1.1790
Max Act: 1.0184. Min Act: -0.0001
Data Index: 605602 (C4 (Web Text))
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.1790. Min Range: -1.1790
Max Act: 0.9778. Min Act: -0.0001
Data Index: 1419210 (Python Code)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.1790. Min Range: -1.1790
Max Act: 1.0072. Min Act: -0.0001
Data Index: 1418673 (Python Code)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.1790. Min Range: -1.1790
Max Act: 0.9949. Min Act: -0.0001
Data Index: 1468962 (Python Code)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.1790. Min Range: -1.1790
Max Act: 0.9087. Min Act: -0.0001
Data Index: 1445050 (Python Code)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.1790. Min Range: -1.1790
Max Act: 0.9672. Min Act: -0.0001
Data Index: 1445676 (Python Code)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.1790. Min Range: -1.1790
Max Act: 0.8709. Min Act: -0.0001
Data Index: 1394940 (Python Code)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.1790. Min Range: -1.1790
Max Act: 0.9574. Min Act: -0.0001
Data Index: 1579762 (Python Code)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.1790. Min Range: -1.1790
Max Act: 0.9530. Min Act: -0.0001
Data Index: 1441265 (Python Code)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #19