Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 224 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 1.6903. Min Range: -1.6903
Max Act: 1.6903. Min Act: -0.0001
Data Index: 1020123 (C4 (Web Text))
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.6903. Min Range: -1.6903
Max Act: 1.5308. Min Act: -0.0001
Data Index: 408039 (C4 (Web Text))
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.6903. Min Range: -1.6903
Max Act: 1.5086. Min Act: -0.0001
Data Index: 79327 (C4 (Web Text))
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.6903. Min Range: -1.6903
Max Act: 1.5972. Min Act: -0.0001
Data Index: 1004315 (C4 (Web Text))
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.6903. Min Range: -1.6903
Max Act: 1.5272. Min Act: -0.0001
Data Index: 1334575 (C4 (Web Text))
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.6903. Min Range: -1.6903
Max Act: 1.6013. Min Act: -0.0001
Data Index: 748128 (C4 (Web Text))
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.6903. Min Range: -1.6903
Max Act: 1.4791. Min Act: -0.0001
Data Index: 300096 (C4 (Web Text))
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.6903. Min Range: -1.6903
Max Act: 1.3580. Min Act: -0.0001
Data Index: 974119 (C4 (Web Text))
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.6903. Min Range: -1.6903
Max Act: 1.6111. Min Act: -0.0001
Data Index: 559324 (C4 (Web Text))
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.6903. Min Range: -1.6903
Max Act: 1.4680. Min Act: -0.0001
Data Index: 42757 (C4 (Web Text))
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.6903. Min Range: -1.6903
Max Act: 1.4686. Min Act: -0.0001
Data Index: 588895 (C4 (Web Text))
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.6903. Min Range: -1.6903
Max Act: 1.3837. Min Act: -0.0001
Data Index: 939644 (C4 (Web Text))
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.6903. Min Range: -1.6903
Max Act: 1.3409. Min Act: -0.0001
Data Index: 1619453 (Python Code)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.6903. Min Range: -1.6903
Max Act: 1.3609. Min Act: -0.0001
Data Index: 720939 (C4 (Web Text))
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.6903. Min Range: -1.6903
Max Act: 1.1252. Min Act: -0.0001
Data Index: 1615435 (Python Code)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.6903. Min Range: -1.6903
Max Act: 1.4571. Min Act: -0.0001
Data Index: 541945 (C4 (Web Text))
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.6903. Min Range: -1.6903
Max Act: 1.5730. Min Act: -0.0001
Data Index: 1109972 (C4 (Web Text))
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.6903. Min Range: -1.6903
Max Act: 1.2902. Min Act: -0.0001
Data Index: 1239939 (C4 (Web Text))
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.6903. Min Range: -1.6903
Max Act: 1.4730. Min Act: -0.0001
Data Index: 905783 (C4 (Web Text))
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.6903. Min Range: -1.6903
Max Act: 1.4879. Min Act: -0.0001
Data Index: 688714 (C4 (Web Text))
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #19