Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: The Pile
Neuron 1592 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')
Text #0
Max Range: 0.1918. Min Range: -0.1918
Max Act: 0.1918. Min Act: -0.0001
Data Index: 297466 (The Pile)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.1918. Min Range: -0.1918
Max Act: 0.1886. Min Act: -0.0001
Data Index: 778264 (The Pile)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.1918. Min Range: -0.1918
Max Act: 0.1589. Min Act: -0.0001
Data Index: 458854 (The Pile)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.1918. Min Range: -0.1918
Max Act: 0.1693. Min Act: -0.0001
Data Index: 1928377 (The Pile)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.1918. Min Range: -0.1918
Max Act: 0.1450. Min Act: -0.0001
Data Index: 1237385 (The Pile)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.1918. Min Range: -0.1918
Max Act: 0.1454. Min Act: -0.0001
Data Index: 1673825 (The Pile)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.1918. Min Range: -0.1918
Max Act: 0.1533. Min Act: -0.0001
Data Index: 1111176 (The Pile)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.1918. Min Range: -0.1918
Max Act: 0.1663. Min Act: -0.0001
Data Index: 492806 (The Pile)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.1918. Min Range: -0.1918
Max Act: 0.1483. Min Act: -0.0001
Data Index: 907644 (The Pile)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.1918. Min Range: -0.1918
Max Act: 0.1438. Min Act: -0.0001
Data Index: 118836 (The Pile)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.1918. Min Range: -0.1918
Max Act: 0.1416. Min Act: -0.0001
Data Index: 1167316 (The Pile)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.1918. Min Range: -0.1918
Max Act: 0.1500. Min Act: -0.0001
Data Index: 1615363 (The Pile)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.1918. Min Range: -0.1918
Max Act: 0.1406. Min Act: -0.0001
Data Index: 939639 (The Pile)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.1918. Min Range: -0.1918
Max Act: 0.1299. Min Act: -0.0001
Data Index: 183998 (The Pile)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.1918. Min Range: -0.1918
Max Act: 0.1307. Min Act: -0.0001
Data Index: 130961 (The Pile)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.1918. Min Range: -0.1918
Max Act: 0.1307. Min Act: -0.0001
Data Index: 92886 (The Pile)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.1918. Min Range: -0.1918
Max Act: 0.1326. Min Act: -0.0001
Data Index: 1166425 (The Pile)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.1918. Min Range: -0.1918
Max Act: 0.1376. Min Act: -0.0001
Data Index: 1878543 (The Pile)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.1918. Min Range: -0.1918
Max Act: 0.1479. Min Act: -0.0001
Data Index: 1878396 (The Pile)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.1918. Min Range: -0.1918
Max Act: 0.1368. Min Act: -0.0001
Data Index: 432786 (The Pile)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #19