Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3388 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 0.4589. Min Range: -0.4589
Max Act: 0.4589. Min Act: -0.0001
Data Index: 1250371 (C4 (Web Text))
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.4589. Min Range: -0.4589
Max Act: 0.4239. Min Act: -0.0001
Data Index: 214806 (C4 (Web Text))
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.4589. Min Range: -0.4589
Max Act: 0.4225. Min Act: -0.0001
Data Index: 438700 (C4 (Web Text))
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.4589. Min Range: -0.4589
Max Act: 0.4483. Min Act: -0.0001
Data Index: 1028500 (C4 (Web Text))
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.4589. Min Range: -0.4589
Max Act: 0.4009. Min Act: -0.0001
Data Index: 53758 (C4 (Web Text))
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.4589. Min Range: -0.4589
Max Act: 0.4024. Min Act: -0.0001
Data Index: 403026 (C4 (Web Text))
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.4589. Min Range: -0.4589
Max Act: 0.3931. Min Act: -0.0001
Data Index: 83861 (C4 (Web Text))
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.4589. Min Range: -0.4589
Max Act: 0.3957. Min Act: -0.0001
Data Index: 642523 (C4 (Web Text))
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.4589. Min Range: -0.4589
Max Act: 0.3643. Min Act: -0.0001
Data Index: 1221977 (C4 (Web Text))
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.4589. Min Range: -0.4589
Max Act: 0.3853. Min Act: -0.0001
Data Index: 184085 (C4 (Web Text))
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.4589. Min Range: -0.4589
Max Act: 0.3858. Min Act: -0.0001
Data Index: 265959 (C4 (Web Text))
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.4589. Min Range: -0.4589
Max Act: 0.4108. Min Act: -0.0001
Data Index: 589494 (C4 (Web Text))
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.4589. Min Range: -0.4589
Max Act: 0.3813. Min Act: -0.0001
Data Index: 126536 (C4 (Web Text))
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.4589. Min Range: -0.4589
Max Act: 0.3819. Min Act: -0.0001
Data Index: 711926 (C4 (Web Text))
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.4589. Min Range: -0.4589
Max Act: 0.3775. Min Act: -0.0001
Data Index: 407185 (C4 (Web Text))
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.4589. Min Range: -0.4589
Max Act: 0.3806. Min Act: -0.0001
Data Index: 135798 (C4 (Web Text))
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.4589. Min Range: -0.4589
Max Act: 0.3860. Min Act: -0.0001
Data Index: 733091 (C4 (Web Text))
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.4589. Min Range: -0.4589
Max Act: 0.3609. Min Act: -0.0001
Data Index: 282121 (C4 (Web Text))
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.4589. Min Range: -0.4589
Max Act: 0.3740. Min Act: -0.0001
Data Index: 558309 (C4 (Web Text))
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.4589. Min Range: -0.4589
Max Act: 0.3828. Min Act: -0.0001
Data Index: 1057057 (C4 (Web Text))
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #19