Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 4087 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 0.8896. Min Range: -0.8896
Max Act: 0.8896. Min Act: -0.0001
Data Index: 239927 (C4 (Web Text))
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.8896. Min Range: -0.8896
Max Act: 0.8307. Min Act: -0.0001
Data Index: 314530 (C4 (Web Text))
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.8896. Min Range: -0.8896
Max Act: 0.8550. Min Act: -0.0001
Data Index: 280333 (C4 (Web Text))
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.8896. Min Range: -0.8896
Max Act: 0.8550. Min Act: -0.0001
Data Index: 665008 (C4 (Web Text))
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.8896. Min Range: -0.8896
Max Act: 0.8367. Min Act: -0.0001
Data Index: 397280 (C4 (Web Text))
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.8896. Min Range: -0.8896
Max Act: 0.8339. Min Act: -0.0001
Data Index: 691672 (C4 (Web Text))
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.8896. Min Range: -0.8896
Max Act: 0.8224. Min Act: -0.0001
Data Index: 856565 (C4 (Web Text))
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.8896. Min Range: -0.8896
Max Act: 0.8106. Min Act: -0.0001
Data Index: 57718 (C4 (Web Text))
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.8896. Min Range: -0.8896
Max Act: 0.8065. Min Act: -0.0001
Data Index: 1001556 (C4 (Web Text))
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.8896. Min Range: -0.8896
Max Act: 0.7997. Min Act: -0.0001
Data Index: 1205820 (C4 (Web Text))
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.8896. Min Range: -0.8896
Max Act: 0.7785. Min Act: -0.0001
Data Index: 1197198 (C4 (Web Text))
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.8896. Min Range: -0.8896
Max Act: 0.8557. Min Act: -0.0001
Data Index: 966005 (C4 (Web Text))
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.8896. Min Range: -0.8896
Max Act: 0.7492. Min Act: -0.0001
Data Index: 403817 (C4 (Web Text))
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.8896. Min Range: -0.8896
Max Act: 0.7647. Min Act: -0.0001
Data Index: 326730 (C4 (Web Text))
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.8896. Min Range: -0.8896
Max Act: 0.7852. Min Act: -0.0001
Data Index: 335928 (C4 (Web Text))
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.8896. Min Range: -0.8896
Max Act: 0.7562. Min Act: -0.0001
Data Index: 137834 (C4 (Web Text))
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.8896. Min Range: -0.8896
Max Act: 0.7791. Min Act: -0.0001
Data Index: 955951 (C4 (Web Text))
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.8896. Min Range: -0.8896
Max Act: 0.7838. Min Act: -0.0001
Data Index: 1078759 (C4 (Web Text))
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.8896. Min Range: -0.8896
Max Act: 0.7577. Min Act: -0.0001
Data Index: 367183 (C4 (Web Text))
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.8896. Min Range: -0.8896
Max Act: 0.7757. Min Act: -0.0001
Data Index: 727620 (C4 (Web Text))
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #19