Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: The Pile
Neuron 2272 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')
Text #0
Max Range: 0.1806. Min Range: -0.1806
Max Act: 0.1806. Min Act: -0.0001
Data Index: 1845449 (The Pile)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.1806. Min Range: -0.1806
Max Act: 0.1745. Min Act: -0.0001
Data Index: 1361293 (The Pile)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.1806. Min Range: -0.1806
Max Act: 0.1660. Min Act: -0.0001
Data Index: 697717 (The Pile)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.1806. Min Range: -0.1806
Max Act: 0.1739. Min Act: -0.0001
Data Index: 549603 (The Pile)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.1806. Min Range: -0.1806
Max Act: 0.1751. Min Act: -0.0001
Data Index: 1451900 (The Pile)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.1806. Min Range: -0.1806
Max Act: 0.1749. Min Act: -0.0001
Data Index: 994806 (The Pile)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.1806. Min Range: -0.1806
Max Act: 0.1638. Min Act: -0.0001
Data Index: 1862240 (The Pile)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.1806. Min Range: -0.1806
Max Act: 0.1682. Min Act: -0.0001
Data Index: 1573301 (The Pile)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.1806. Min Range: -0.1806
Max Act: 0.1719. Min Act: -0.0001
Data Index: 198997 (The Pile)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.1806. Min Range: -0.1806
Max Act: 0.1660. Min Act: -0.0001
Data Index: 103751 (The Pile)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.1806. Min Range: -0.1806
Max Act: 0.1596. Min Act: -0.0001
Data Index: 812532 (The Pile)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.1806. Min Range: -0.1806
Max Act: 0.1587. Min Act: -0.0001
Data Index: 432619 (The Pile)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.1806. Min Range: -0.1806
Max Act: 0.1642. Min Act: -0.0001
Data Index: 1814617 (The Pile)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.1806. Min Range: -0.1806
Max Act: 0.1552. Min Act: -0.0001
Data Index: 1051661 (The Pile)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.1806. Min Range: -0.1806
Max Act: 0.1586. Min Act: -0.0001
Data Index: 393403 (The Pile)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.1806. Min Range: -0.1806
Max Act: 0.1588. Min Act: -0.0001
Data Index: 1869726 (The Pile)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.1806. Min Range: -0.1806
Max Act: 0.1589. Min Act: -0.0001
Data Index: 1882844 (The Pile)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.1806. Min Range: -0.1806
Max Act: 0.1563. Min Act: -0.0001
Data Index: 1323 (The Pile)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.1806. Min Range: -0.1806
Max Act: 0.1506. Min Act: -0.0001
Data Index: 973587 (The Pile)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.1806. Min Range: -0.1806
Max Act: 0.1697. Min Act: -0.0001
Data Index: 1641148 (The Pile)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #19