Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: The Pile
Neuron 653 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')
Text #0
Max Range: 0.7477. Min Range: -0.7477
Max Act: 0.6902. Min Act: -0.0001
Data Index: 1913452 (The Pile)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.7477. Min Range: -0.7477
Max Act: 0.7477. Min Act: -0.0001
Data Index: 1848816 (The Pile)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.7477. Min Range: -0.7477
Max Act: 0.6517. Min Act: -0.0001
Data Index: 1021987 (The Pile)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.7477. Min Range: -0.7477
Max Act: 0.6724. Min Act: -0.0001
Data Index: 1739069 (The Pile)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.7477. Min Range: -0.7477
Max Act: 0.6377. Min Act: -0.0001
Data Index: 64468 (The Pile)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.7477. Min Range: -0.7477
Max Act: 0.5566. Min Act: -0.0001
Data Index: 1234416 (The Pile)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.7477. Min Range: -0.7477
Max Act: 0.5600. Min Act: -0.0001
Data Index: 157544 (The Pile)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.7477. Min Range: -0.7477
Max Act: 0.5400. Min Act: -0.0001
Data Index: 268095 (The Pile)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.7477. Min Range: -0.7477
Max Act: 0.6124. Min Act: -0.0001
Data Index: 388783 (The Pile)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.7477. Min Range: -0.7477
Max Act: 0.5560. Min Act: -0.0001
Data Index: 494631 (The Pile)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.7477. Min Range: -0.7477
Max Act: 0.5373. Min Act: -0.0001
Data Index: 1790391 (The Pile)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.7477. Min Range: -0.7477
Max Act: 0.5564. Min Act: -0.0001
Data Index: 1728184 (The Pile)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.7477. Min Range: -0.7477
Max Act: 0.6549. Min Act: -0.0001
Data Index: 1640642 (The Pile)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.7477. Min Range: -0.7477
Max Act: 0.6142. Min Act: -0.0001
Data Index: 1156338 (The Pile)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.7477. Min Range: -0.7477
Max Act: 0.6271. Min Act: -0.0001
Data Index: 44324 (The Pile)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.7477. Min Range: -0.7477
Max Act: 0.6114. Min Act: -0.0001
Data Index: 39182 (The Pile)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.7477. Min Range: -0.7477
Max Act: 0.6762. Min Act: -0.0001
Data Index: 269974 (The Pile)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.7477. Min Range: -0.7477
Max Act: 0.5940. Min Act: -0.0001
Data Index: 315016 (The Pile)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.7477. Min Range: -0.7477
Max Act: 0.6146. Min Act: -0.0001
Data Index: 732329 (The Pile)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.7477. Min Range: -0.7477
Max Act: 0.6047. Min Act: -0.0001
Data Index: 849583 (The Pile)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #19