Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2763 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 2.1210. Min Range: -2.1210
Max Act: 2.1210. Min Act: -0.0001
Data Index: 227403 (C4 (Web Text))
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.1210. Min Range: -2.1210
Max Act: 1.9770. Min Act: -0.0001
Data Index: 174358 (C4 (Web Text))
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.1210. Min Range: -2.1210
Max Act: 1.9418. Min Act: -0.0001
Data Index: 798827 (C4 (Web Text))
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.1210. Min Range: -2.1210
Max Act: 1.8595. Min Act: -0.0001
Data Index: 624742 (C4 (Web Text))
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.1210. Min Range: -2.1210
Max Act: 1.6278. Min Act: -0.0001
Data Index: 891369 (C4 (Web Text))
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.1210. Min Range: -2.1210
Max Act: 1.5933. Min Act: -0.0001
Data Index: 365306 (C4 (Web Text))
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.1210. Min Range: -2.1210
Max Act: 1.7783. Min Act: -0.0001
Data Index: 1126869 (C4 (Web Text))
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.1210. Min Range: -2.1210
Max Act: 1.6361. Min Act: -0.0001
Data Index: 1222765 (C4 (Web Text))
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.1210. Min Range: -2.1210
Max Act: 1.4666. Min Act: -0.0001
Data Index: 123226 (C4 (Web Text))
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.1210. Min Range: -2.1210
Max Act: 1.6124. Min Act: -0.0001
Data Index: 286833 (C4 (Web Text))
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.1210. Min Range: -2.1210
Max Act: 1.6762. Min Act: -0.0001
Data Index: 1254009 (C4 (Web Text))
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.1210. Min Range: -2.1210
Max Act: 1.5995. Min Act: -0.0001
Data Index: 1348436 (C4 (Web Text))
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.1210. Min Range: -2.1210
Max Act: 1.6748. Min Act: -0.0001
Data Index: 178067 (C4 (Web Text))
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.1210. Min Range: -2.1210
Max Act: 1.6788. Min Act: -0.0001
Data Index: 909968 (C4 (Web Text))
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.1210. Min Range: -2.1210
Max Act: 1.5796. Min Act: -0.0001
Data Index: 314933 (C4 (Web Text))
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.1210. Min Range: -2.1210
Max Act: 1.6480. Min Act: -0.0001
Data Index: 145992 (C4 (Web Text))
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.1210. Min Range: -2.1210
Max Act: 1.6535. Min Act: -0.0001
Data Index: 1021879 (C4 (Web Text))
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.1210. Min Range: -2.1210
Max Act: 1.7210. Min Act: -0.0001
Data Index: 1000677 (C4 (Web Text))
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.1210. Min Range: -2.1210
Max Act: 1.6480. Min Act: -0.0001
Data Index: 160339 (C4 (Web Text))
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.1210. Min Range: -2.1210
Max Act: 1.5594. Min Act: -0.0001
Data Index: 1619 (C4 (Web Text))
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #19