Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3366 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 1.7862. Min Range: -1.7862
Max Act: 1.7862. Min Act: -0.0001
Data Index: 262551 (C4 (Web Text))
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.7862. Min Range: -1.7862
Max Act: 1.6667. Min Act: -0.0001
Data Index: 812358 (C4 (Web Text))
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.7862. Min Range: -1.7862
Max Act: 1.2703. Min Act: -0.0001
Data Index: 747562 (C4 (Web Text))
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.7862. Min Range: -1.7862
Max Act: 1.4623. Min Act: -0.0001
Data Index: 144585 (C4 (Web Text))
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.7862. Min Range: -1.7862
Max Act: 1.3526. Min Act: -0.0001
Data Index: 878763 (C4 (Web Text))
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.7862. Min Range: -1.7862
Max Act: 1.3353. Min Act: -0.0001
Data Index: 923053 (C4 (Web Text))
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.7862. Min Range: -1.7862
Max Act: 1.2921. Min Act: -0.0001
Data Index: 150187 (C4 (Web Text))
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.7862. Min Range: -1.7862
Max Act: 1.1969. Min Act: -0.0001
Data Index: 891386 (C4 (Web Text))
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.7862. Min Range: -1.7862
Max Act: 1.1762. Min Act: -0.0001
Data Index: 1196822 (C4 (Web Text))
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.7862. Min Range: -1.7862
Max Act: 1.2867. Min Act: -0.0001
Data Index: 1315976 (C4 (Web Text))
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.7862. Min Range: -1.7862
Max Act: 1.2741. Min Act: -0.0001
Data Index: 1084776 (C4 (Web Text))
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.7862. Min Range: -1.7862
Max Act: 1.2619. Min Act: -0.0001
Data Index: 1179351 (C4 (Web Text))
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.7862. Min Range: -1.7862
Max Act: 1.0952. Min Act: -0.0001
Data Index: 158980 (C4 (Web Text))
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.7862. Min Range: -1.7862
Max Act: 1.1277. Min Act: -0.0001
Data Index: 473560 (C4 (Web Text))
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.7862. Min Range: -1.7862
Max Act: 1.2997. Min Act: -0.0001
Data Index: 901631 (C4 (Web Text))
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.7862. Min Range: -1.7862
Max Act: 1.2182. Min Act: -0.0001
Data Index: 110824 (C4 (Web Text))
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.7862. Min Range: -1.7862
Max Act: 1.1886. Min Act: -0.0001
Data Index: 1072398 (C4 (Web Text))
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.7862. Min Range: -1.7862
Max Act: 1.1143. Min Act: -0.0001
Data Index: 1280541 (C4 (Web Text))
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.7862. Min Range: -1.7862
Max Act: 1.3529. Min Act: -0.0001
Data Index: 696916 (C4 (Web Text))
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.7862. Min Range: -1.7862
Max Act: 1.1752. Min Act: -0.0001
Data Index: 340151 (C4 (Web Text))
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #19