Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 4049 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 2.5868. Min Range: -2.5868
Max Act: 2.5868. Min Act: -0.0001
Data Index: 1094606 (C4 (Web Text))
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5868. Min Range: -2.5868
Max Act: 2.2808. Min Act: -0.0001
Data Index: 1268896 (C4 (Web Text))
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5868. Min Range: -2.5868
Max Act: 2.3345. Min Act: -0.0001
Data Index: 1060587 (C4 (Web Text))
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5868. Min Range: -2.5868
Max Act: 2.0447. Min Act: -0.0001
Data Index: 157606 (C4 (Web Text))
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5868. Min Range: -2.5868
Max Act: 1.8650. Min Act: -0.0001
Data Index: 19598 (C4 (Web Text))
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5868. Min Range: -2.5868
Max Act: 1.7226. Min Act: -0.0001
Data Index: 67619 (C4 (Web Text))
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5868. Min Range: -2.5868
Max Act: 1.7667. Min Act: -0.0001
Data Index: 1022444 (C4 (Web Text))
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5868. Min Range: -2.5868
Max Act: 1.7656. Min Act: -0.0001
Data Index: 514097 (C4 (Web Text))
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5868. Min Range: -2.5868
Max Act: 1.7741. Min Act: -0.0000
Data Index: 518252 (C4 (Web Text))
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5868. Min Range: -2.5868
Max Act: 1.6985. Min Act: -0.0001
Data Index: 99397 (C4 (Web Text))
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5868. Min Range: -2.5868
Max Act: 1.6713. Min Act: -0.0001
Data Index: 470851 (C4 (Web Text))
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5868. Min Range: -2.5868
Max Act: 1.6458. Min Act: -0.0001
Data Index: 700474 (C4 (Web Text))
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5868. Min Range: -2.5868
Max Act: 1.6481. Min Act: -0.0001
Data Index: 974993 (C4 (Web Text))
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5868. Min Range: -2.5868
Max Act: 1.4372. Min Act: -0.0000
Data Index: 54154 (C4 (Web Text))
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5868. Min Range: -2.5868
Max Act: 1.5320. Min Act: -0.0001
Data Index: 363453 (C4 (Web Text))
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5868. Min Range: -2.5868
Max Act: 1.6123. Min Act: -0.0000
Data Index: 749574 (C4 (Web Text))
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5868. Min Range: -2.5868
Max Act: 1.5395. Min Act: -0.0000
Data Index: 924577 (C4 (Web Text))
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5868. Min Range: -2.5868
Max Act: 1.5478. Min Act: -0.0001
Data Index: 1311526 (C4 (Web Text))
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5868. Min Range: -2.5868
Max Act: 1.4656. Min Act: -0.0000
Data Index: 740603 (C4 (Web Text))
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5868. Min Range: -2.5868
Max Act: 1.4498. Min Act: -0.0000
Data Index: 1282742 (C4 (Web Text))
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #19