Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3696 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 1.0926. Min Range: -1.0926
Max Act: 1.0926. Min Act: -0.0001
Data Index: 145563 (C4 (Web Text))
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.0926. Min Range: -1.0926
Max Act: 1.0134. Min Act: -0.0001
Data Index: 607873 (C4 (Web Text))
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.0926. Min Range: -1.0926
Max Act: 0.9955. Min Act: -0.0001
Data Index: 450983 (C4 (Web Text))
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.0926. Min Range: -1.0926
Max Act: 1.0229. Min Act: -0.0001
Data Index: 1234598 (C4 (Web Text))
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.0926. Min Range: -1.0926
Max Act: 0.8431. Min Act: -0.0001
Data Index: 202472 (C4 (Web Text))
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.0926. Min Range: -1.0926
Max Act: 0.9721. Min Act: -0.0001
Data Index: 176008 (C4 (Web Text))
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.0926. Min Range: -1.0926
Max Act: 0.9552. Min Act: -0.0001
Data Index: 849544 (C4 (Web Text))
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.0926. Min Range: -1.0926
Max Act: 0.9286. Min Act: -0.0001
Data Index: 1115917 (C4 (Web Text))
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.0926. Min Range: -1.0926
Max Act: 0.8608. Min Act: -0.0001
Data Index: 126102 (C4 (Web Text))
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.0926. Min Range: -1.0926
Max Act: 0.8820. Min Act: -0.0001
Data Index: 475736 (C4 (Web Text))
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.0926. Min Range: -1.0926
Max Act: 0.8529. Min Act: -0.0001
Data Index: 781598 (C4 (Web Text))
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.0926. Min Range: -1.0926
Max Act: 0.8774. Min Act: -0.0001
Data Index: 377018 (C4 (Web Text))
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.0926. Min Range: -1.0926
Max Act: 0.8430. Min Act: -0.0001
Data Index: 332414 (C4 (Web Text))
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.0926. Min Range: -1.0926
Max Act: 0.8646. Min Act: -0.0001
Data Index: 1011514 (C4 (Web Text))
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.0926. Min Range: -1.0926
Max Act: 0.7601. Min Act: -0.0001
Data Index: 949972 (C4 (Web Text))
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.0926. Min Range: -1.0926
Max Act: 0.8030. Min Act: -0.0001
Data Index: 820228 (C4 (Web Text))
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.0926. Min Range: -1.0926
Max Act: 0.8200. Min Act: -0.0001
Data Index: 1131053 (C4 (Web Text))
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.0926. Min Range: -1.0926
Max Act: 0.8173. Min Act: -0.0001
Data Index: 1321611 (C4 (Web Text))
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.0926. Min Range: -1.0926
Max Act: 0.8024. Min Act: -0.0001
Data Index: 1030842 (C4 (Web Text))
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.0926. Min Range: -1.0926
Max Act: 0.7339. Min Act: -0.0001
Data Index: 979097 (C4 (Web Text))
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #19