Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: The Pile
Neuron 1043 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')
Text #0
Max Range: 3.4372. Min Range: -3.4372
Max Act: 3.4372. Min Act: -0.0000
Data Index: 857508 (The Pile)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4372. Min Range: -3.4372
Max Act: 2.9801. Min Act: -0.0000
Data Index: 717961 (The Pile)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4372. Min Range: -3.4372
Max Act: 3.0287. Min Act: -0.0000
Data Index: 816905 (The Pile)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4372. Min Range: -3.4372
Max Act: 2.9824. Min Act: -0.0000
Data Index: 1076133 (The Pile)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4372. Min Range: -3.4372
Max Act: 2.6517. Min Act: -0.0000
Data Index: 848336 (The Pile)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4372. Min Range: -3.4372
Max Act: 2.7958. Min Act: -0.0000
Data Index: 1427029 (The Pile)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4372. Min Range: -3.4372
Max Act: 2.7569. Min Act: -0.0000
Data Index: 570690 (The Pile)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4372. Min Range: -3.4372
Max Act: 2.7993. Min Act: -0.0000
Data Index: 463185 (The Pile)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4372. Min Range: -3.4372
Max Act: 2.7063. Min Act: -0.0000
Data Index: 192516 (The Pile)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4372. Min Range: -3.4372
Max Act: 2.6919. Min Act: -0.0000
Data Index: 636738 (The Pile)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4372. Min Range: -3.4372
Max Act: 2.7943. Min Act: -0.0000
Data Index: 709088 (The Pile)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4372. Min Range: -3.4372
Max Act: 2.7125. Min Act: -0.0000
Data Index: 725124 (The Pile)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4372. Min Range: -3.4372
Max Act: 2.4170. Min Act: -0.0000
Data Index: 629566 (The Pile)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4372. Min Range: -3.4372
Max Act: 2.5249. Min Act: -0.0000
Data Index: 1586420 (The Pile)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4372. Min Range: -3.4372
Max Act: 2.7316. Min Act: -0.0000
Data Index: 1314625 (The Pile)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4372. Min Range: -3.4372
Max Act: 2.2226. Min Act: -0.0000
Data Index: 64886 (The Pile)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4372. Min Range: -3.4372
Max Act: 2.3302. Min Act: -0.0000
Data Index: 1756601 (The Pile)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4372. Min Range: -3.4372
Max Act: 2.3250. Min Act: -0.0000
Data Index: 911569 (The Pile)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4372. Min Range: -3.4372
Max Act: 2.5778. Min Act: -0.0000
Data Index: 1703987 (The Pile)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4372. Min Range: -3.4372
Max Act: 2.5530. Min Act: -0.0000
Data Index: 225189 (The Pile)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #19