Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2219 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 2.2110. Min Range: -2.2110
Max Act: 2.2110. Min Act: -0.0001
Data Index: 786998 (C4 (Web Text))
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.2110. Min Range: -2.2110
Max Act: 2.1269. Min Act: -0.0001
Data Index: 747551 (C4 (Web Text))
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.2110. Min Range: -2.2110
Max Act: 2.1619. Min Act: -0.0001
Data Index: 76061 (C4 (Web Text))
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.2110. Min Range: -2.2110
Max Act: 2.1183. Min Act: -0.0001
Data Index: 661965 (C4 (Web Text))
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.2110. Min Range: -2.2110
Max Act: 2.0790. Min Act: -0.0001
Data Index: 814046 (C4 (Web Text))
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.2110. Min Range: -2.2110
Max Act: 1.9605. Min Act: -0.0001
Data Index: 635605 (C4 (Web Text))
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.2110. Min Range: -2.2110
Max Act: 1.8702. Min Act: -0.0001
Data Index: 544732 (C4 (Web Text))
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.2110. Min Range: -2.2110
Max Act: 1.8609. Min Act: -0.0001
Data Index: 68031 (C4 (Web Text))
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.2110. Min Range: -2.2110
Max Act: 1.9470. Min Act: -0.0001
Data Index: 709035 (C4 (Web Text))
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.2110. Min Range: -2.2110
Max Act: 1.9238. Min Act: -0.0001
Data Index: 567397 (C4 (Web Text))
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.2110. Min Range: -2.2110
Max Act: 1.9121. Min Act: -0.0001
Data Index: 1590710 (Python Code)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.2110. Min Range: -2.2110
Max Act: 1.9271. Min Act: -0.0001
Data Index: 1147979 (C4 (Web Text))
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.2110. Min Range: -2.2110
Max Act: 1.9865. Min Act: -0.0001
Data Index: 442939 (C4 (Web Text))
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.2110. Min Range: -2.2110
Max Act: 1.8471. Min Act: -0.0001
Data Index: 874353 (C4 (Web Text))
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.2110. Min Range: -2.2110
Max Act: 1.8516. Min Act: -0.0001
Data Index: 821533 (C4 (Web Text))
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.2110. Min Range: -2.2110
Max Act: 1.7060. Min Act: -0.0001
Data Index: 74044 (C4 (Web Text))
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.2110. Min Range: -2.2110
Max Act: 1.7917. Min Act: -0.0001
Data Index: 693742 (C4 (Web Text))
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.2110. Min Range: -2.2110
Max Act: 1.6249. Min Act: -0.0001
Data Index: 599658 (C4 (Web Text))
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.2110. Min Range: -2.2110
Max Act: 1.6938. Min Act: -0.0001
Data Index: 764891 (C4 (Web Text))
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.2110. Min Range: -2.2110
Max Act: 1.8977. Min Act: -0.0001
Data Index: 1153375 (C4 (Web Text))
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #19