Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3005 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 3.3772. Min Range: -3.3772
Max Act: 3.3772. Min Act: -0.0001
Data Index: 934012 (C4 (Web Text))
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3772. Min Range: -3.3772
Max Act: 2.9147. Min Act: -0.0001
Data Index: 460000 (C4 (Web Text))
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3772. Min Range: -3.3772
Max Act: 2.2893. Min Act: -0.0001
Data Index: 799230 (C4 (Web Text))
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3772. Min Range: -3.3772
Max Act: 2.5999. Min Act: -0.0001
Data Index: 183463 (C4 (Web Text))
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3772. Min Range: -3.3772
Max Act: 2.3955. Min Act: -0.0001
Data Index: 665756 (C4 (Web Text))
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3772. Min Range: -3.3772
Max Act: 2.4911. Min Act: -0.0001
Data Index: 1013178 (C4 (Web Text))
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3772. Min Range: -3.3772
Max Act: 2.5028. Min Act: -0.0001
Data Index: 238362 (C4 (Web Text))
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3772. Min Range: -3.3772
Max Act: 2.3342. Min Act: -0.0001
Data Index: 929840 (C4 (Web Text))
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3772. Min Range: -3.3772
Max Act: 2.5515. Min Act: -0.0001
Data Index: 1067342 (C4 (Web Text))
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3772. Min Range: -3.3772
Max Act: 2.4176. Min Act: -0.0001
Data Index: 305290 (C4 (Web Text))
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3772. Min Range: -3.3772
Max Act: 2.3876. Min Act: -0.0001
Data Index: 377917 (C4 (Web Text))
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3772. Min Range: -3.3772
Max Act: 2.3586. Min Act: -0.0001
Data Index: 1125344 (C4 (Web Text))
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3772. Min Range: -3.3772
Max Act: 2.2013. Min Act: -0.0001
Data Index: 488418 (C4 (Web Text))
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3772. Min Range: -3.3772
Max Act: 2.3439. Min Act: -0.0001
Data Index: 409686 (C4 (Web Text))
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3772. Min Range: -3.3772
Max Act: 2.0756. Min Act: -0.0001
Data Index: 373654 (C4 (Web Text))
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3772. Min Range: -3.3772
Max Act: 1.9189. Min Act: -0.0001
Data Index: 279405 (C4 (Web Text))
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3772. Min Range: -3.3772
Max Act: 2.2171. Min Act: -0.0001
Data Index: 690930 (C4 (Web Text))
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3772. Min Range: -3.3772
Max Act: 2.0746. Min Act: -0.0001
Data Index: 1255465 (C4 (Web Text))
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3772. Min Range: -3.3772
Max Act: 2.2023. Min Act: -0.0001
Data Index: 1049625 (C4 (Web Text))
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3772. Min Range: -3.3772
Max Act: 1.8623. Min Act: -0.0001
Data Index: 86270 (C4 (Web Text))
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #19