Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 5059 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 0.5794. Min Range: -0.5794
Max Act: 0.5794. Min Act: -0.0001
Data Index: 87133 (C4 (Web Text))
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.5794. Min Range: -0.5794
Max Act: 0.5537. Min Act: -0.0001
Data Index: 812504 (C4 (Web Text))
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.5794. Min Range: -0.5794
Max Act: 0.5330. Min Act: -0.0001
Data Index: 1355471 (C4 (Web Text))
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.5794. Min Range: -0.5794
Max Act: 0.4839. Min Act: -0.0001
Data Index: 857401 (C4 (Web Text))
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.5794. Min Range: -0.5794
Max Act: 0.4468. Min Act: -0.0001
Data Index: 420886 (C4 (Web Text))
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.5794. Min Range: -0.5794
Max Act: 0.4870. Min Act: -0.0001
Data Index: 397588 (C4 (Web Text))
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.5794. Min Range: -0.5794
Max Act: 0.4673. Min Act: -0.0001
Data Index: 1402113 (Python Code)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.5794. Min Range: -0.5794
Max Act: 0.3886. Min Act: -0.0001
Data Index: 417565 (C4 (Web Text))
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.5794. Min Range: -0.5794
Max Act: 0.4050. Min Act: -0.0001
Data Index: 1170220 (C4 (Web Text))
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.5794. Min Range: -0.5794
Max Act: 0.4522. Min Act: -0.0001
Data Index: 377317 (C4 (Web Text))
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.5794. Min Range: -0.5794
Max Act: 0.4227. Min Act: -0.0001
Data Index: 658312 (C4 (Web Text))
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.5794. Min Range: -0.5794
Max Act: 0.4074. Min Act: -0.0001
Data Index: 1335306 (C4 (Web Text))
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.5794. Min Range: -0.5794
Max Act: 0.4309. Min Act: -0.0001
Data Index: 417628 (C4 (Web Text))
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.5794. Min Range: -0.5794
Max Act: 0.3984. Min Act: -0.0001
Data Index: 1520677 (Python Code)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.5794. Min Range: -0.5794
Max Act: 0.4051. Min Act: -0.0001
Data Index: 68838 (C4 (Web Text))
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.5794. Min Range: -0.5794
Max Act: 0.4772. Min Act: -0.0001
Data Index: 1021627 (C4 (Web Text))
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.5794. Min Range: -0.5794
Max Act: 0.4101. Min Act: -0.0001
Data Index: 87640 (C4 (Web Text))
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.5794. Min Range: -0.5794
Max Act: 0.4063. Min Act: -0.0001
Data Index: 670828 (C4 (Web Text))
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.5794. Min Range: -0.5794
Max Act: 0.3993. Min Act: -0.0001
Data Index: 163016 (C4 (Web Text))
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.5794. Min Range: -0.5794
Max Act: 0.3992. Min Act: -0.0001
Data Index: 87528 (C4 (Web Text))
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #19