Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 4047 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 2.7694. Min Range: -2.7694
Max Act: 2.2861. Min Act: -0.0001
Data Index: 1111353 (C4 (Web Text))
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7694. Min Range: -2.7694
Max Act: 2.6906. Min Act: -0.0001
Data Index: 272916 (C4 (Web Text))
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7694. Min Range: -2.7694
Max Act: 2.7694. Min Act: -0.0001
Data Index: 1084280 (C4 (Web Text))
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7694. Min Range: -2.7694
Max Act: 2.1076. Min Act: -0.0001
Data Index: 507544 (C4 (Web Text))
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7694. Min Range: -2.7694
Max Act: 2.3060. Min Act: -0.0001
Data Index: 1025975 (C4 (Web Text))
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7694. Min Range: -2.7694
Max Act: 2.1727. Min Act: -0.0001
Data Index: 466789 (C4 (Web Text))
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7694. Min Range: -2.7694
Max Act: 1.9474. Min Act: -0.0001
Data Index: 920203 (C4 (Web Text))
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7694. Min Range: -2.7694
Max Act: 2.2180. Min Act: -0.0001
Data Index: 1063689 (C4 (Web Text))
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7694. Min Range: -2.7694
Max Act: 2.0344. Min Act: -0.0001
Data Index: 536042 (C4 (Web Text))
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7694. Min Range: -2.7694
Max Act: 1.8782. Min Act: -0.0001
Data Index: 689489 (C4 (Web Text))
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7694. Min Range: -2.7694
Max Act: 2.2852. Min Act: -0.0001
Data Index: 812130 (C4 (Web Text))
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7694. Min Range: -2.7694
Max Act: 2.4679. Min Act: -0.0001
Data Index: 1247373 (C4 (Web Text))
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7694. Min Range: -2.7694
Max Act: 1.9820. Min Act: -0.0001
Data Index: 926559 (C4 (Web Text))
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7694. Min Range: -2.7694
Max Act: 1.9876. Min Act: -0.0001
Data Index: 665823 (C4 (Web Text))
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7694. Min Range: -2.7694
Max Act: 1.5884. Min Act: -0.0001
Data Index: 798372 (C4 (Web Text))
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7694. Min Range: -2.7694
Max Act: 1.8601. Min Act: -0.0001
Data Index: 577375 (C4 (Web Text))
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7694. Min Range: -2.7694
Max Act: 1.6995. Min Act: -0.0001
Data Index: 855662 (C4 (Web Text))
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7694. Min Range: -2.7694
Max Act: 1.7717. Min Act: -0.0001
Data Index: 68785 (C4 (Web Text))
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7694. Min Range: -2.7694
Max Act: 1.9627. Min Act: -0.0001
Data Index: 790686 (C4 (Web Text))
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7694. Min Range: -2.7694
Max Act: 1.8900. Min Act: -0.0001
Data Index: 1032314 (C4 (Web Text))
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #19