Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: The Pile
Neuron 1233 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')
Text #0
Max Range: 1.0111. Min Range: -1.0111
Max Act: 1.0111. Min Act: -0.0001
Data Index: 122051 (The Pile)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.0111. Min Range: -1.0111
Max Act: 0.9123. Min Act: -0.0001
Data Index: 1630876 (The Pile)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.0111. Min Range: -1.0111
Max Act: 0.8631. Min Act: -0.0001
Data Index: 250520 (The Pile)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.0111. Min Range: -1.0111
Max Act: 0.8666. Min Act: -0.0001
Data Index: 908454 (The Pile)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.0111. Min Range: -1.0111
Max Act: 0.8506. Min Act: -0.0001
Data Index: 354024 (The Pile)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.0111. Min Range: -1.0111
Max Act: 0.7754. Min Act: -0.0001
Data Index: 1076764 (The Pile)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.0111. Min Range: -1.0111
Max Act: 0.8236. Min Act: -0.0001
Data Index: 1550361 (The Pile)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.0111. Min Range: -1.0111
Max Act: 0.7685. Min Act: -0.0001
Data Index: 102075 (The Pile)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.0111. Min Range: -1.0111
Max Act: 0.8056. Min Act: -0.0001
Data Index: 77528 (The Pile)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.0111. Min Range: -1.0111
Max Act: 0.7951. Min Act: -0.0001
Data Index: 761362 (The Pile)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.0111. Min Range: -1.0111
Max Act: 0.8139. Min Act: -0.0001
Data Index: 1224944 (The Pile)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.0111. Min Range: -1.0111
Max Act: 0.7754. Min Act: -0.0001
Data Index: 926216 (The Pile)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.0111. Min Range: -1.0111
Max Act: 0.8145. Min Act: -0.0001
Data Index: 24750 (The Pile)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.0111. Min Range: -1.0111
Max Act: 0.7887. Min Act: -0.0001
Data Index: 500291 (The Pile)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.0111. Min Range: -1.0111
Max Act: 0.7699. Min Act: -0.0001
Data Index: 1540489 (The Pile)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.0111. Min Range: -1.0111
Max Act: 0.7424. Min Act: -0.0001
Data Index: 1024675 (The Pile)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.0111. Min Range: -1.0111
Max Act: 0.7215. Min Act: -0.0001
Data Index: 9812 (The Pile)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.0111. Min Range: -1.0111
Max Act: 0.7510. Min Act: -0.0001
Data Index: 1774347 (The Pile)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.0111. Min Range: -1.0111
Max Act: 0.7561. Min Act: -0.0001
Data Index: 1534312 (The Pile)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.0111. Min Range: -1.0111
Max Act: 0.7629. Min Act: -0.0001
Data Index: 1548237 (The Pile)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #19