Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1703 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 1.7978. Min Range: -1.7978
Max Act: 1.7978. Min Act: -0.0001
Data Index: 451505 (C4 (Web Text))
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.7978. Min Range: -1.7978
Max Act: 1.7522. Min Act: -0.0001
Data Index: 962422 (C4 (Web Text))
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.7978. Min Range: -1.7978
Max Act: 1.6928. Min Act: -0.0001
Data Index: 557810 (C4 (Web Text))
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.7978. Min Range: -1.7978
Max Act: 1.4798. Min Act: -0.0001
Data Index: 1590559 (Python Code)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.7978. Min Range: -1.7978
Max Act: 1.4314. Min Act: -0.0001
Data Index: 160180 (C4 (Web Text))
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.7978. Min Range: -1.7978
Max Act: 1.5360. Min Act: -0.0001
Data Index: 1413616 (Python Code)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.7978. Min Range: -1.7978
Max Act: 1.4652. Min Act: -0.0001
Data Index: 368124 (C4 (Web Text))
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.7978. Min Range: -1.7978
Max Act: 1.4640. Min Act: -0.0001
Data Index: 1575995 (Python Code)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.7978. Min Range: -1.7978
Max Act: 1.4131. Min Act: -0.0001
Data Index: 1174765 (C4 (Web Text))
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.7978. Min Range: -1.7978
Max Act: 1.4051. Min Act: -0.0001
Data Index: 1634306 (Python Code)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.7978. Min Range: -1.7978
Max Act: 1.2814. Min Act: -0.0001
Data Index: 1378501 (Python Code)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.7978. Min Range: -1.7978
Max Act: 1.4013. Min Act: -0.0001
Data Index: 1333079 (C4 (Web Text))
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.7978. Min Range: -1.7978
Max Act: 1.3047. Min Act: -0.0001
Data Index: 1576017 (Python Code)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.7978. Min Range: -1.7978
Max Act: 1.3514. Min Act: -0.0001
Data Index: 1577748 (Python Code)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.7978. Min Range: -1.7978
Max Act: 1.2558. Min Act: -0.0001
Data Index: 1506228 (Python Code)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.7978. Min Range: -1.7978
Max Act: 1.3823. Min Act: -0.0001
Data Index: 646722 (C4 (Web Text))
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.7978. Min Range: -1.7978
Max Act: 1.3710. Min Act: -0.0001
Data Index: 577309 (C4 (Web Text))
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.7978. Min Range: -1.7978
Max Act: 1.3975. Min Act: -0.0001
Data Index: 1172190 (C4 (Web Text))
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.7978. Min Range: -1.7978
Max Act: 1.3279. Min Act: -0.0001
Data Index: 1481953 (Python Code)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.7978. Min Range: -1.7978
Max Act: 1.3194. Min Act: -0.0001
Data Index: 1454091 (Python Code)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #19