Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3022 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 0.9766. Min Range: -0.9766
Max Act: 0.9420. Min Act: -0.0001
Data Index: 116330 (C4 (Web Text))
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.9766. Min Range: -0.9766
Max Act: 0.9766. Min Act: -0.0001
Data Index: 381663 (C4 (Web Text))
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.9766. Min Range: -0.9766
Max Act: 0.8748. Min Act: -0.0001
Data Index: 950878 (C4 (Web Text))
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.9766. Min Range: -0.9766
Max Act: 0.7647. Min Act: -0.0001
Data Index: 782342 (C4 (Web Text))
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.9766. Min Range: -0.9766
Max Act: 0.8300. Min Act: -0.0001
Data Index: 1239453 (C4 (Web Text))
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.9766. Min Range: -0.9766
Max Act: 0.7624. Min Act: -0.0001
Data Index: 492872 (C4 (Web Text))
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.9766. Min Range: -0.9766
Max Act: 0.7621. Min Act: -0.0001
Data Index: 605283 (C4 (Web Text))
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.9766. Min Range: -0.9766
Max Act: 0.7513. Min Act: -0.0001
Data Index: 1115712 (C4 (Web Text))
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.9766. Min Range: -0.9766
Max Act: 0.6875. Min Act: -0.0001
Data Index: 1178989 (C4 (Web Text))
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.9766. Min Range: -0.9766
Max Act: 0.7005. Min Act: -0.0001
Data Index: 773098 (C4 (Web Text))
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.9766. Min Range: -0.9766
Max Act: 0.6325. Min Act: -0.0001
Data Index: 349997 (C4 (Web Text))
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.9766. Min Range: -0.9766
Max Act: 0.7013. Min Act: -0.0001
Data Index: 285101 (C4 (Web Text))
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.9766. Min Range: -0.9766
Max Act: 0.7230. Min Act: -0.0001
Data Index: 601629 (C4 (Web Text))
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.9766. Min Range: -0.9766
Max Act: 0.6977. Min Act: -0.0001
Data Index: 138587 (C4 (Web Text))
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.9766. Min Range: -0.9766
Max Act: 0.7032. Min Act: -0.0001
Data Index: 456204 (C4 (Web Text))
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.9766. Min Range: -0.9766
Max Act: 0.6566. Min Act: -0.0001
Data Index: 49634 (C4 (Web Text))
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.9766. Min Range: -0.9766
Max Act: 0.6431. Min Act: -0.0001
Data Index: 360295 (C4 (Web Text))
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.9766. Min Range: -0.9766
Max Act: 0.6756. Min Act: -0.0001
Data Index: 936412 (C4 (Web Text))
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.9766. Min Range: -0.9766
Max Act: 0.6707. Min Act: -0.0001
Data Index: 1082180 (C4 (Web Text))
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.9766. Min Range: -0.9766
Max Act: 0.6458. Min Act: -0.0001
Data Index: 1304407 (C4 (Web Text))
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #19