Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2975 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 2.2936. Min Range: -2.2936
Max Act: 2.1820. Min Act: -0.0001
Data Index: 114018 (C4 (Web Text))
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.2936. Min Range: -2.2936
Max Act: 2.2936. Min Act: -0.0001
Data Index: 184137 (C4 (Web Text))
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.2936. Min Range: -2.2936
Max Act: 2.2832. Min Act: -0.0001
Data Index: 989070 (C4 (Web Text))
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.2936. Min Range: -2.2936
Max Act: 2.1237. Min Act: -0.0001
Data Index: 521517 (C4 (Web Text))
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.2936. Min Range: -2.2936
Max Act: 2.0983. Min Act: -0.0001
Data Index: 978675 (C4 (Web Text))
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.2936. Min Range: -2.2936
Max Act: 1.9739. Min Act: -0.0001
Data Index: 740576 (C4 (Web Text))
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.2936. Min Range: -2.2936
Max Act: 2.0844. Min Act: -0.0001
Data Index: 290874 (C4 (Web Text))
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.2936. Min Range: -2.2936
Max Act: 2.0367. Min Act: -0.0001
Data Index: 447882 (C4 (Web Text))
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.2936. Min Range: -2.2936
Max Act: 2.0327. Min Act: -0.0001
Data Index: 968234 (C4 (Web Text))
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.2936. Min Range: -2.2936
Max Act: 2.0289. Min Act: -0.0001
Data Index: 629853 (C4 (Web Text))
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.2936. Min Range: -2.2936
Max Act: 1.8288. Min Act: -0.0001
Data Index: 760720 (C4 (Web Text))
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.2936. Min Range: -2.2936
Max Act: 1.7954. Min Act: -0.0001
Data Index: 1359476 (C4 (Web Text))
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.2936. Min Range: -2.2936
Max Act: 2.0070. Min Act: -0.0001
Data Index: 720600 (C4 (Web Text))
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.2936. Min Range: -2.2936
Max Act: 2.0054. Min Act: -0.0001
Data Index: 53427 (C4 (Web Text))
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.2936. Min Range: -2.2936
Max Act: 1.6861. Min Act: -0.0001
Data Index: 801404 (C4 (Web Text))
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.2936. Min Range: -2.2936
Max Act: 1.8704. Min Act: -0.0001
Data Index: 1469937 (Python Code)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.2936. Min Range: -2.2936
Max Act: 1.9827. Min Act: -0.0001
Data Index: 448783 (C4 (Web Text))
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.2936. Min Range: -2.2936
Max Act: 1.5943. Min Act: -0.0001
Data Index: 1237088 (C4 (Web Text))
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.2936. Min Range: -2.2936
Max Act: 2.0709. Min Act: -0.0001
Data Index: 1278680 (C4 (Web Text))
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.2936. Min Range: -2.2936
Max Act: 1.7651. Min Act: -0.0001
Data Index: 624062 (C4 (Web Text))
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #19