Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2536 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 0.0937. Min Range: -0.0937
Max Act: 0.0937. Min Act: -0.0001
Data Index: 741055 (C4 (Web Text))
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.0937. Min Range: -0.0937
Max Act: 0.0845. Min Act: -0.0001
Data Index: 754045 (C4 (Web Text))
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.0937. Min Range: -0.0937
Max Act: 0.0863. Min Act: -0.0001
Data Index: 581475 (C4 (Web Text))
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.0937. Min Range: -0.0937
Max Act: 0.0781. Min Act: -0.0001
Data Index: 112139 (C4 (Web Text))
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.0937. Min Range: -0.0937
Max Act: 0.0899. Min Act: -0.0001
Data Index: 1174124 (C4 (Web Text))
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.0937. Min Range: -0.0937
Max Act: 0.0830. Min Act: -0.0001
Data Index: 488978 (C4 (Web Text))
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.0937. Min Range: -0.0937
Max Act: 0.0749. Min Act: -0.0001
Data Index: 61115 (C4 (Web Text))
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.0937. Min Range: -0.0937
Max Act: 0.0857. Min Act: -0.0001
Data Index: 1067133 (C4 (Web Text))
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.0937. Min Range: -0.0937
Max Act: 0.0780. Min Act: -0.0001
Data Index: 453616 (C4 (Web Text))
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.0937. Min Range: -0.0937
Max Act: 0.0771. Min Act: -0.0001
Data Index: 896810 (C4 (Web Text))
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.0937. Min Range: -0.0937
Max Act: 0.0731. Min Act: -0.0001
Data Index: 813423 (C4 (Web Text))
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.0937. Min Range: -0.0937
Max Act: 0.0697. Min Act: -0.0001
Data Index: 324597 (C4 (Web Text))
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.0937. Min Range: -0.0937
Max Act: 0.0629. Min Act: -0.0001
Data Index: 1118988 (C4 (Web Text))
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.0937. Min Range: -0.0937
Max Act: 0.0811. Min Act: -0.0001
Data Index: 1084649 (C4 (Web Text))
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.0937. Min Range: -0.0937
Max Act: 0.0580. Min Act: -0.0001
Data Index: 1481893 (Python Code)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.0937. Min Range: -0.0937
Max Act: 0.0584. Min Act: -0.0001
Data Index: 697599 (C4 (Web Text))
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.0937. Min Range: -0.0937
Max Act: 0.0573. Min Act: -0.0001
Data Index: 1587874 (Python Code)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.0937. Min Range: -0.0937
Max Act: 0.0560. Min Act: -0.0001
Data Index: 721973 (C4 (Web Text))
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.0937. Min Range: -0.0937
Max Act: 0.0610. Min Act: -0.0001
Data Index: 455466 (C4 (Web Text))
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.0937. Min Range: -0.0937
Max Act: 0.0569. Min Act: -0.0001
Data Index: 1564636 (Python Code)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #19