Model: SoLU Model: 4 Layers, 2048 Neurons per Layer
Dataset: The Pile
Neuron 694 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l-pile')
Text #0
Max Range: 0.0855. Min Range: -0.0855
Max Act: 0.0855. Min Act: -0.0001
Data Index: 1079253 (The Pile)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.0855. Min Range: -0.0855
Max Act: 0.0642. Min Act: -0.0001
Data Index: 55426 (The Pile)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.0855. Min Range: -0.0855
Max Act: 0.0614. Min Act: -0.0001
Data Index: 1275126 (The Pile)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.0855. Min Range: -0.0855
Max Act: 0.0618. Min Act: -0.0001
Data Index: 1677629 (The Pile)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.0855. Min Range: -0.0855
Max Act: 0.0615. Min Act: -0.0001
Data Index: 1986463 (The Pile)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.0855. Min Range: -0.0855
Max Act: 0.0587. Min Act: -0.0001
Data Index: 37107 (The Pile)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.0855. Min Range: -0.0855
Max Act: 0.0583. Min Act: -0.0001
Data Index: 1427888 (The Pile)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.0855. Min Range: -0.0855
Max Act: 0.0589. Min Act: -0.0001
Data Index: 1621737 (The Pile)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.0855. Min Range: -0.0855
Max Act: 0.0580. Min Act: -0.0001
Data Index: 1933783 (The Pile)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.0855. Min Range: -0.0855
Max Act: 0.0566. Min Act: -0.0001
Data Index: 345471 (The Pile)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.0855. Min Range: -0.0855
Max Act: 0.0543. Min Act: -0.0001
Data Index: 1882426 (The Pile)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.0855. Min Range: -0.0855
Max Act: 0.0576. Min Act: -0.0001
Data Index: 1865567 (The Pile)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.0855. Min Range: -0.0855
Max Act: 0.0535. Min Act: -0.0001
Data Index: 80641 (The Pile)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.0855. Min Range: -0.0855
Max Act: 0.0503. Min Act: -0.0001
Data Index: 164994 (The Pile)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.0855. Min Range: -0.0855
Max Act: 0.0520. Min Act: -0.0001
Data Index: 1509322 (The Pile)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.0855. Min Range: -0.0855
Max Act: 0.0499. Min Act: -0.0001
Data Index: 1563746 (The Pile)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.0855. Min Range: -0.0855
Max Act: 0.0511. Min Act: -0.0001
Data Index: 1210976 (The Pile)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.0855. Min Range: -0.0855
Max Act: 0.0510. Min Act: -0.0001
Data Index: 545423 (The Pile)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.0855. Min Range: -0.0855
Max Act: 0.0503. Min Act: -0.0001
Data Index: 564067 (The Pile)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.0855. Min Range: -0.0855
Max Act: 0.0504. Min Act: -0.0001
Data Index: 1664541 (The Pile)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #19