Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1016 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 1.9039. Min Range: -1.9039
Max Act: 1.9039. Min Act: -0.0001
Data Index: 375104 (C4 (Web Text))
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.9039. Min Range: -1.9039
Max Act: 1.7591. Min Act: -0.0002
Data Index: 301244 (C4 (Web Text))
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.9039. Min Range: -1.9039
Max Act: 1.5546. Min Act: -0.0002
Data Index: 42343 (C4 (Web Text))
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.9039. Min Range: -1.9039
Max Act: 1.6482. Min Act: -0.0001
Data Index: 1259201 (C4 (Web Text))
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.9039. Min Range: -1.9039
Max Act: 1.7311. Min Act: -0.0002
Data Index: 1193542 (C4 (Web Text))
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.9039. Min Range: -1.9039
Max Act: 1.4349. Min Act: -0.0001
Data Index: 25439 (C4 (Web Text))
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.9039. Min Range: -1.9039
Max Act: 1.3930. Min Act: -0.0001
Data Index: 76895 (C4 (Web Text))
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.9039. Min Range: -1.9039
Max Act: 1.7515. Min Act: -0.0001
Data Index: 229856 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.9039. Min Range: -1.9039
Max Act: 1.5046. Min Act: -0.0001
Data Index: 514876 (C4 (Web Text))
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.9039. Min Range: -1.9039
Max Act: 1.6320. Min Act: -0.0001
Data Index: 586831 (C4 (Web Text))
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.9039. Min Range: -1.9039
Max Act: 1.6026. Min Act: -0.0001
Data Index: 1353229 (C4 (Web Text))
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.9039. Min Range: -1.9039
Max Act: 1.4433. Min Act: -0.0001
Data Index: 222810 (C4 (Web Text))
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.9039. Min Range: -1.9039
Max Act: 1.3993. Min Act: -0.0002
Data Index: 414960 (C4 (Web Text))
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.9039. Min Range: -1.9039
Max Act: 1.3794. Min Act: -0.0001
Data Index: 557398 (C4 (Web Text))
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.9039. Min Range: -1.9039
Max Act: 1.4860. Min Act: -0.0001
Data Index: 1352711 (C4 (Web Text))
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.9039. Min Range: -1.9039
Max Act: 1.3446. Min Act: -0.0001
Data Index: 365787 (C4 (Web Text))
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.9039. Min Range: -1.9039
Max Act: 1.4234. Min Act: -0.0002
Data Index: 314639 (C4 (Web Text))
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.9039. Min Range: -1.9039
Max Act: 1.3839. Min Act: -0.0001
Data Index: 1131831 (C4 (Web Text))
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.9039. Min Range: -1.9039
Max Act: 1.4437. Min Act: -0.0001
Data Index: 244873 (C4 (Web Text))
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.9039. Min Range: -1.9039
Max Act: 1.4522. Min Act: -0.0001
Data Index: 112868 (C4 (Web Text))
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #19