Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 4097 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 2.0800. Min Range: -2.0800
Max Act: 1.8587. Min Act: -0.0000
Data Index: 1342926 (C4 (Web Text))
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.0800. Min Range: -2.0800
Max Act: 2.0800. Min Act: -0.0000
Data Index: 1094903 (C4 (Web Text))
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.0800. Min Range: -2.0800
Max Act: 1.7652. Min Act: -0.0000
Data Index: 1307224 (C4 (Web Text))
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.0800. Min Range: -2.0800
Max Act: 1.7217. Min Act: -0.0000
Data Index: 128781 (C4 (Web Text))
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.0800. Min Range: -2.0800
Max Act: 1.6174. Min Act: -0.0000
Data Index: 776058 (C4 (Web Text))
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.0800. Min Range: -2.0800
Max Act: 1.5708. Min Act: -0.0000
Data Index: 155782 (C4 (Web Text))
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.0800. Min Range: -2.0800
Max Act: 1.5048. Min Act: -0.0000
Data Index: 1239566 (C4 (Web Text))
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.0800. Min Range: -2.0800
Max Act: 1.5787. Min Act: -0.0000
Data Index: 1199306 (C4 (Web Text))
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.0800. Min Range: -2.0800
Max Act: 1.5387. Min Act: -0.0000
Data Index: 1294635 (C4 (Web Text))
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.0800. Min Range: -2.0800
Max Act: 1.4918. Min Act: -0.0000
Data Index: 1050266 (C4 (Web Text))
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.0800. Min Range: -2.0800
Max Act: 1.3942. Min Act: -0.0000
Data Index: 161855 (C4 (Web Text))
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.0800. Min Range: -2.0800
Max Act: 1.5641. Min Act: -0.0000
Data Index: 40032 (C4 (Web Text))
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.0800. Min Range: -2.0800
Max Act: 1.5386. Min Act: -0.0000
Data Index: 1207129 (C4 (Web Text))
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.0800. Min Range: -2.0800
Max Act: 1.4396. Min Act: -0.0000
Data Index: 1156483 (C4 (Web Text))
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.0800. Min Range: -2.0800
Max Act: 1.4357. Min Act: -0.0000
Data Index: 504764 (C4 (Web Text))
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.0800. Min Range: -2.0800
Max Act: 1.4252. Min Act: -0.0000
Data Index: 455059 (C4 (Web Text))
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.0800. Min Range: -2.0800
Max Act: 1.4311. Min Act: -0.0000
Data Index: 735155 (C4 (Web Text))
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.0800. Min Range: -2.0800
Max Act: 1.3540. Min Act: -0.0000
Data Index: 162331 (C4 (Web Text))
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.0800. Min Range: -2.0800
Max Act: 1.4107. Min Act: -0.0000
Data Index: 1039073 (C4 (Web Text))
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.0800. Min Range: -2.0800
Max Act: 1.2158. Min Act: -0.0000
Data Index: 1204737 (C4 (Web Text))
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #19