Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 10 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 1.2014. Min Range: -1.2014
Max Act: 1.2014. Min Act: -0.0001
Data Index: 358937 (C4 (Web Text))
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.2014. Min Range: -1.2014
Max Act: 0.8894. Min Act: -0.0001
Data Index: 859404 (C4 (Web Text))
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.2014. Min Range: -1.2014
Max Act: 0.7855. Min Act: -0.0001
Data Index: 241797 (C4 (Web Text))
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.2014. Min Range: -1.2014
Max Act: 1.1244. Min Act: -0.0001
Data Index: 488878 (C4 (Web Text))
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.2014. Min Range: -1.2014
Max Act: 1.0086. Min Act: -0.0001
Data Index: 356266 (C4 (Web Text))
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.2014. Min Range: -1.2014
Max Act: 1.1207. Min Act: -0.0001
Data Index: 535006 (C4 (Web Text))
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.2014. Min Range: -1.2014
Max Act: 1.0938. Min Act: -0.0001
Data Index: 675814 (C4 (Web Text))
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.2014. Min Range: -1.2014
Max Act: 1.0108. Min Act: -0.0001
Data Index: 874227 (C4 (Web Text))
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.2014. Min Range: -1.2014
Max Act: 1.0088. Min Act: -0.0001
Data Index: 312648 (C4 (Web Text))
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.2014. Min Range: -1.2014
Max Act: 1.0050. Min Act: -0.0001
Data Index: 399100 (C4 (Web Text))
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.2014. Min Range: -1.2014
Max Act: 0.9548. Min Act: -0.0001
Data Index: 214756 (C4 (Web Text))
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.2014. Min Range: -1.2014
Max Act: 0.8901. Min Act: -0.0001
Data Index: 797458 (C4 (Web Text))
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.2014. Min Range: -1.2014
Max Act: 1.0027. Min Act: -0.0001
Data Index: 611334 (C4 (Web Text))
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.2014. Min Range: -1.2014
Max Act: 1.0297. Min Act: -0.0001
Data Index: 971851 (C4 (Web Text))
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.2014. Min Range: -1.2014
Max Act: 0.9018. Min Act: -0.0001
Data Index: 952578 (C4 (Web Text))
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.2014. Min Range: -1.2014
Max Act: 1.0079. Min Act: -0.0001
Data Index: 254904 (C4 (Web Text))
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.2014. Min Range: -1.2014
Max Act: 1.0092. Min Act: -0.0001
Data Index: 1157805 (C4 (Web Text))
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.2014. Min Range: -1.2014
Max Act: 1.0668. Min Act: -0.0001
Data Index: 1067359 (C4 (Web Text))
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.2014. Min Range: -1.2014
Max Act: 0.8823. Min Act: -0.0001
Data Index: 973222 (C4 (Web Text))
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.2014. Min Range: -1.2014
Max Act: 1.0627. Min Act: -0.0001
Data Index: 629820 (C4 (Web Text))
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #19