Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: The Pile
Neuron 1673 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')
Text #0
Max Range: 2.6530. Min Range: -2.6530
Max Act: 2.6366. Min Act: -0.0000
Data Index: 631037 (The Pile)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.6530. Min Range: -2.6530
Max Act: 2.6530. Min Act: -0.0000
Data Index: 865800 (The Pile)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.6530. Min Range: -2.6530
Max Act: 2.5455. Min Act: -0.0000
Data Index: 451546 (The Pile)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.6530. Min Range: -2.6530
Max Act: 2.2689. Min Act: -0.0000
Data Index: 245117 (The Pile)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.6530. Min Range: -2.6530
Max Act: 2.5191. Min Act: -0.0000
Data Index: 646243 (The Pile)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.6530. Min Range: -2.6530
Max Act: 2.4659. Min Act: -0.0000
Data Index: 631042 (The Pile)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.6530. Min Range: -2.6530
Max Act: 2.5808. Min Act: -0.0000
Data Index: 771318 (The Pile)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.6530. Min Range: -2.6530
Max Act: 2.4040. Min Act: -0.0000
Data Index: 674670 (The Pile)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.6530. Min Range: -2.6530
Max Act: 2.1611. Min Act: -0.0000
Data Index: 1519829 (The Pile)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.6530. Min Range: -2.6530
Max Act: 2.0315. Min Act: -0.0000
Data Index: 89767 (The Pile)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.6530. Min Range: -2.6530
Max Act: 1.9092. Min Act: -0.0000
Data Index: 1067450 (The Pile)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.6530. Min Range: -2.6530
Max Act: 2.0603. Min Act: -0.0000
Data Index: 1536123 (The Pile)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.6530. Min Range: -2.6530
Max Act: 2.0158. Min Act: -0.0000
Data Index: 1469828 (The Pile)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.6530. Min Range: -2.6530
Max Act: 1.8004. Min Act: -0.0000
Data Index: 1037485 (The Pile)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.6530. Min Range: -2.6530
Max Act: 1.9904. Min Act: -0.0000
Data Index: 1170083 (The Pile)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.6530. Min Range: -2.6530
Max Act: 1.8846. Min Act: -0.0000
Data Index: 370560 (The Pile)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.6530. Min Range: -2.6530
Max Act: 2.0668. Min Act: -0.0000
Data Index: 234576 (The Pile)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.6530. Min Range: -2.6530
Max Act: 2.0086. Min Act: -0.0000
Data Index: 315125 (The Pile)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.6530. Min Range: -2.6530
Max Act: 1.9693. Min Act: -0.0000
Data Index: 41015 (The Pile)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.6530. Min Range: -2.6530
Max Act: 1.7127. Min Act: -0.0000
Data Index: 236228 (The Pile)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #19