Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: The Pile
Neuron 826 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')
Text #0
Max Range: 1.9673. Min Range: -1.9673
Max Act: 1.9673. Min Act: -0.0000
Data Index: 871684 (The Pile)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.9673. Min Range: -1.9673
Max Act: 1.6956. Min Act: -0.0000
Data Index: 437434 (The Pile)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.9673. Min Range: -1.9673
Max Act: 1.6616. Min Act: -0.0000
Data Index: 905165 (The Pile)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.9673. Min Range: -1.9673
Max Act: 1.6522. Min Act: -0.0000
Data Index: 24726 (The Pile)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.9673. Min Range: -1.9673
Max Act: 1.6377. Min Act: -0.0000
Data Index: 1775107 (The Pile)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.9673. Min Range: -1.9673
Max Act: 1.6335. Min Act: -0.0001
Data Index: 1343304 (The Pile)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.9673. Min Range: -1.9673
Max Act: 1.3991. Min Act: -0.0000
Data Index: 945934 (The Pile)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.9673. Min Range: -1.9673
Max Act: 1.5986. Min Act: -0.0000
Data Index: 1693123 (The Pile)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.9673. Min Range: -1.9673
Max Act: 1.5804. Min Act: -0.0000
Data Index: 383286 (The Pile)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.9673. Min Range: -1.9673
Max Act: 1.5584. Min Act: -0.0000
Data Index: 1875373 (The Pile)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.9673. Min Range: -1.9673
Max Act: 1.4665. Min Act: -0.0000
Data Index: 1355174 (The Pile)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.9673. Min Range: -1.9673
Max Act: 1.5963. Min Act: -0.0000
Data Index: 163406 (The Pile)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.9673. Min Range: -1.9673
Max Act: 1.5156. Min Act: -0.0001
Data Index: 1391091 (The Pile)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.9673. Min Range: -1.9673
Max Act: 1.5075. Min Act: -0.0000
Data Index: 1644655 (The Pile)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.9673. Min Range: -1.9673
Max Act: 1.5992. Min Act: -0.0000
Data Index: 751610 (The Pile)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.9673. Min Range: -1.9673
Max Act: 1.6917. Min Act: -0.0000
Data Index: 360793 (The Pile)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.9673. Min Range: -1.9673
Max Act: 1.4943. Min Act: -0.0000
Data Index: 1405007 (The Pile)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.9673. Min Range: -1.9673
Max Act: 1.4951. Min Act: -0.0000
Data Index: 1781662 (The Pile)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.9673. Min Range: -1.9673
Max Act: 1.4682. Min Act: -0.0000
Data Index: 1816562 (The Pile)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.9673. Min Range: -1.9673
Max Act: 1.3829. Min Act: -0.0000
Data Index: 1801821 (The Pile)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #19