Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 603 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 3.8849. Min Range: -3.8849
Max Act: 3.8849. Min Act: -0.0001
Data Index: 101532 (C4 (Web Text))
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8849. Min Range: -3.8849
Max Act: 3.7468. Min Act: -0.0001
Data Index: 1050611 (C4 (Web Text))
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8849. Min Range: -3.8849
Max Act: 3.5707. Min Act: -0.0001
Data Index: 278655 (C4 (Web Text))
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8849. Min Range: -3.8849
Max Act: 3.4238. Min Act: -0.0001
Data Index: 1152294 (C4 (Web Text))
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8849. Min Range: -3.8849
Max Act: 3.3229. Min Act: -0.0001
Data Index: 521042 (C4 (Web Text))
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8849. Min Range: -3.8849
Max Act: 3.1159. Min Act: -0.0001
Data Index: 1017642 (C4 (Web Text))
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8849. Min Range: -3.8849
Max Act: 3.1771. Min Act: -0.0001
Data Index: 449663 (C4 (Web Text))
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8849. Min Range: -3.8849
Max Act: 2.5910. Min Act: -0.0001
Data Index: 921336 (C4 (Web Text))
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8849. Min Range: -3.8849
Max Act: 2.6682. Min Act: -0.0001
Data Index: 584438 (C4 (Web Text))
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8849. Min Range: -3.8849
Max Act: 2.9115. Min Act: -0.0001
Data Index: 454956 (C4 (Web Text))
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8849. Min Range: -3.8849
Max Act: 2.6014. Min Act: -0.0001
Data Index: 919118 (C4 (Web Text))
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8849. Min Range: -3.8849
Max Act: 2.7254. Min Act: -0.0001
Data Index: 856031 (C4 (Web Text))
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8849. Min Range: -3.8849
Max Act: 2.6840. Min Act: -0.0001
Data Index: 759295 (C4 (Web Text))
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8849. Min Range: -3.8849
Max Act: 2.7728. Min Act: -0.0001
Data Index: 783408 (C4 (Web Text))
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8849. Min Range: -3.8849
Max Act: 1.9552. Min Act: -0.0001
Data Index: 651614 (C4 (Web Text))
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8849. Min Range: -3.8849
Max Act: 2.1008. Min Act: -0.0001
Data Index: 326569 (C4 (Web Text))
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8849. Min Range: -3.8849
Max Act: 2.5634. Min Act: -0.0001
Data Index: 1319975 (C4 (Web Text))
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8849. Min Range: -3.8849
Max Act: 2.1895. Min Act: -0.0001
Data Index: 381527 (C4 (Web Text))
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8849. Min Range: -3.8849
Max Act: 2.6601. Min Act: -0.0001
Data Index: 65841 (C4 (Web Text))
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8849. Min Range: -3.8849
Max Act: 2.1766. Min Act: -0.0001
Data Index: 256961 (C4 (Web Text))
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #19