Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 4131 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 1.5165. Min Range: -1.5165
Max Act: 1.5165. Min Act: -0.0001
Data Index: 47119 (C4 (Web Text))
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.5165. Min Range: -1.5165
Max Act: 1.2737. Min Act: -0.0001
Data Index: 457602 (C4 (Web Text))
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.5165. Min Range: -1.5165
Max Act: 1.0615. Min Act: -0.0001
Data Index: 1089331 (C4 (Web Text))
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.5165. Min Range: -1.5165
Max Act: 1.0607. Min Act: -0.0001
Data Index: 611121 (C4 (Web Text))
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.5165. Min Range: -1.5165
Max Act: 1.1834. Min Act: -0.0001
Data Index: 796286 (C4 (Web Text))
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.5165. Min Range: -1.5165
Max Act: 1.1223. Min Act: -0.0001
Data Index: 497760 (C4 (Web Text))
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.5165. Min Range: -1.5165
Max Act: 1.0771. Min Act: -0.0001
Data Index: 574883 (C4 (Web Text))
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.5165. Min Range: -1.5165
Max Act: 0.9802. Min Act: -0.0001
Data Index: 75531 (C4 (Web Text))
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.5165. Min Range: -1.5165
Max Act: 1.0839. Min Act: -0.0001
Data Index: 1115194 (C4 (Web Text))
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.5165. Min Range: -1.5165
Max Act: 0.9875. Min Act: -0.0001
Data Index: 481230 (C4 (Web Text))
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.5165. Min Range: -1.5165
Max Act: 0.9857. Min Act: -0.0001
Data Index: 451266 (C4 (Web Text))
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.5165. Min Range: -1.5165
Max Act: 0.9959. Min Act: -0.0001
Data Index: 671743 (C4 (Web Text))
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.5165. Min Range: -1.5165
Max Act: 0.9189. Min Act: -0.0001
Data Index: 636939 (C4 (Web Text))
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.5165. Min Range: -1.5165
Max Act: 0.9901. Min Act: -0.0001
Data Index: 496655 (C4 (Web Text))
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.5165. Min Range: -1.5165
Max Act: 0.9800. Min Act: -0.0001
Data Index: 368942 (C4 (Web Text))
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.5165. Min Range: -1.5165
Max Act: 0.8775. Min Act: -0.0001
Data Index: 485482 (C4 (Web Text))
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.5165. Min Range: -1.5165
Max Act: 0.9282. Min Act: -0.0001
Data Index: 851797 (C4 (Web Text))
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.5165. Min Range: -1.5165
Max Act: 0.9508. Min Act: -0.0001
Data Index: 1162411 (C4 (Web Text))
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.5165. Min Range: -1.5165
Max Act: 1.0021. Min Act: -0.0001
Data Index: 1123076 (C4 (Web Text))
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.5165. Min Range: -1.5165
Max Act: 0.9455. Min Act: -0.0001
Data Index: 709850 (C4 (Web Text))
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #19