Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3590 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 2.1111. Min Range: -2.1111
Max Act: 2.1111. Min Act: -0.0001
Data Index: 1193832 (C4 (Web Text))
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.1111. Min Range: -2.1111
Max Act: 2.0330. Min Act: -0.0001
Data Index: 1131887 (C4 (Web Text))
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.1111. Min Range: -2.1111
Max Act: 1.9263. Min Act: -0.0001
Data Index: 1187916 (C4 (Web Text))
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.1111. Min Range: -2.1111
Max Act: 2.0096. Min Act: -0.0001
Data Index: 46725 (C4 (Web Text))
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.1111. Min Range: -2.1111
Max Act: 1.7984. Min Act: -0.0001
Data Index: 642757 (C4 (Web Text))
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.1111. Min Range: -2.1111
Max Act: 1.8718. Min Act: -0.0001
Data Index: 110844 (C4 (Web Text))
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.1111. Min Range: -2.1111
Max Act: 1.8708. Min Act: -0.0001
Data Index: 1289107 (C4 (Web Text))
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.1111. Min Range: -2.1111
Max Act: 1.8482. Min Act: -0.0001
Data Index: 439408 (C4 (Web Text))
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.1111. Min Range: -2.1111
Max Act: 1.8435. Min Act: -0.0001
Data Index: 1257725 (C4 (Web Text))
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.1111. Min Range: -2.1111
Max Act: 1.8239. Min Act: -0.0001
Data Index: 41903 (C4 (Web Text))
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.1111. Min Range: -2.1111
Max Act: 1.8132. Min Act: -0.0001
Data Index: 40125 (C4 (Web Text))
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.1111. Min Range: -2.1111
Max Act: 1.7934. Min Act: -0.0001
Data Index: 30770 (C4 (Web Text))
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.1111. Min Range: -2.1111
Max Act: 1.7935. Min Act: -0.0001
Data Index: 1251238 (C4 (Web Text))
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.1111. Min Range: -2.1111
Max Act: 1.8875. Min Act: -0.0001
Data Index: 1096708 (C4 (Web Text))
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.1111. Min Range: -2.1111
Max Act: 1.6932. Min Act: -0.0001
Data Index: 685250 (C4 (Web Text))
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.1111. Min Range: -2.1111
Max Act: 1.7795. Min Act: -0.0001
Data Index: 652523 (C4 (Web Text))
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.1111. Min Range: -2.1111
Max Act: 1.7669. Min Act: -0.0001
Data Index: 1088411 (C4 (Web Text))
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.1111. Min Range: -2.1111
Max Act: 1.7701. Min Act: -0.0001
Data Index: 775817 (C4 (Web Text))
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.1111. Min Range: -2.1111
Max Act: 1.7536. Min Act: -0.0001
Data Index: 206456 (C4 (Web Text))
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.1111. Min Range: -2.1111
Max Act: 1.7476. Min Act: -0.0001
Data Index: 237898 (C4 (Web Text))
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #19