Model: SoLU Model: 6 Layers, 3072 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 918 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')
Text #0
Max Range: 0.7090. Min Range: -0.7090
Max Act: 0.7090. Min Act: -0.0001
Data Index: 1161148 (C4 (Web Text))
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.7090. Min Range: -0.7090
Max Act: 0.6337. Min Act: -0.0001
Data Index: 1464868 (Python Code)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.7090. Min Range: -0.7090
Max Act: 0.4937. Min Act: -0.0001
Data Index: 591450 (C4 (Web Text))
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.7090. Min Range: -0.7090
Max Act: 0.4593. Min Act: -0.0001
Data Index: 316407 (C4 (Web Text))
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.7090. Min Range: -0.7090
Max Act: 0.4004. Min Act: -0.0001
Data Index: 692678 (C4 (Web Text))
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.7090. Min Range: -0.7090
Max Act: 0.4332. Min Act: -0.0001
Data Index: 1650168 (Python Code)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.7090. Min Range: -0.7090
Max Act: 0.4366. Min Act: -0.0001
Data Index: 1600815 (Python Code)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.7090. Min Range: -0.7090
Max Act: 0.4086. Min Act: -0.0001
Data Index: 561817 (C4 (Web Text))
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.7090. Min Range: -0.7090
Max Act: 0.3947. Min Act: -0.0001
Data Index: 1614998 (Python Code)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.7090. Min Range: -0.7090
Max Act: 0.3312. Min Act: -0.0001
Data Index: 127786 (C4 (Web Text))
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.7090. Min Range: -0.7090
Max Act: 0.3768. Min Act: -0.0001
Data Index: 472670 (C4 (Web Text))
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.7090. Min Range: -0.7090
Max Act: 0.3859. Min Act: -0.0001
Data Index: 869429 (C4 (Web Text))
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.7090. Min Range: -0.7090
Max Act: 0.3829. Min Act: -0.0001
Data Index: 86470 (C4 (Web Text))
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.7090. Min Range: -0.7090
Max Act: 0.3816. Min Act: -0.0001
Data Index: 1109425 (C4 (Web Text))
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.7090. Min Range: -0.7090
Max Act: 0.3534. Min Act: -0.0001
Data Index: 532499 (C4 (Web Text))
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.7090. Min Range: -0.7090
Max Act: 0.3714. Min Act: -0.0001
Data Index: 1477886 (Python Code)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.7090. Min Range: -0.7090
Max Act: 0.3591. Min Act: -0.0001
Data Index: 424223 (C4 (Web Text))
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.7090. Min Range: -0.7090
Max Act: 0.3580. Min Act: -0.0001
Data Index: 1591185 (Python Code)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.7090. Min Range: -0.7090
Max Act: 0.3691. Min Act: -0.0001
Data Index: 1477674 (Python Code)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.7090. Min Range: -0.7090
Max Act: 0.3785. Min Act: -0.0001
Data Index: 282678 (C4 (Web Text))
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #19