Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1323 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 2.7872. Min Range: -2.7872
Max Act: 2.7872. Min Act: -0.0001
Data Index: 860045 (C4 (Web Text))
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7872. Min Range: -2.7872
Max Act: 2.3222. Min Act: -0.0001
Data Index: 1182678 (C4 (Web Text))
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7872. Min Range: -2.7872
Max Act: 2.7206. Min Act: -0.0001
Data Index: 216118 (C4 (Web Text))
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7872. Min Range: -2.7872
Max Act: 2.5706. Min Act: -0.0001
Data Index: 186849 (C4 (Web Text))
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7872. Min Range: -2.7872
Max Act: 2.5652. Min Act: -0.0001
Data Index: 464638 (C4 (Web Text))
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7872. Min Range: -2.7872
Max Act: 2.5734. Min Act: -0.0001
Data Index: 750325 (C4 (Web Text))
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7872. Min Range: -2.7872
Max Act: 2.5890. Min Act: -0.0001
Data Index: 18853 (C4 (Web Text))
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7872. Min Range: -2.7872
Max Act: 2.4667. Min Act: -0.0001
Data Index: 1044012 (C4 (Web Text))
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7872. Min Range: -2.7872
Max Act: 2.5890. Min Act: -0.0001
Data Index: 488893 (C4 (Web Text))
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7872. Min Range: -2.7872
Max Act: 2.5738. Min Act: -0.0001
Data Index: 470341 (C4 (Web Text))
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7872. Min Range: -2.7872
Max Act: 2.5802. Min Act: -0.0001
Data Index: 948255 (C4 (Web Text))
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7872. Min Range: -2.7872
Max Act: 2.4798. Min Act: -0.0001
Data Index: 1178574 (C4 (Web Text))
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7872. Min Range: -2.7872
Max Act: 2.4556. Min Act: -0.0001
Data Index: 380300 (C4 (Web Text))
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7872. Min Range: -2.7872
Max Act: 2.5640. Min Act: -0.0001
Data Index: 843469 (C4 (Web Text))
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7872. Min Range: -2.7872
Max Act: 2.5497. Min Act: -0.0001
Data Index: 774216 (C4 (Web Text))
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7872. Min Range: -2.7872
Max Act: 2.5402. Min Act: -0.0001
Data Index: 906384 (C4 (Web Text))
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7872. Min Range: -2.7872
Max Act: 2.4418. Min Act: -0.0001
Data Index: 1342394 (C4 (Web Text))
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7872. Min Range: -2.7872
Max Act: 2.5525. Min Act: -0.0001
Data Index: 814699 (C4 (Web Text))
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7872. Min Range: -2.7872
Max Act: 2.1757. Min Act: -0.0001
Data Index: 779613 (C4 (Web Text))
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7872. Min Range: -2.7872
Max Act: 2.6528. Min Act: -0.0001
Data Index: 419525 (C4 (Web Text))
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #19