Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: The Pile
Neuron 882 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')
Text #0
Max Range: 0.1885. Min Range: -0.1885
Max Act: 0.1606. Min Act: -0.0001
Data Index: 75375 (The Pile)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.1885. Min Range: -0.1885
Max Act: 0.1715. Min Act: -0.0001
Data Index: 1500180 (The Pile)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.1885. Min Range: -0.1885
Max Act: 0.1885. Min Act: -0.0001
Data Index: 1308247 (The Pile)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.1885. Min Range: -0.1885
Max Act: 0.1670. Min Act: -0.0001
Data Index: 1975746 (The Pile)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.1885. Min Range: -0.1885
Max Act: 0.1645. Min Act: -0.0001
Data Index: 735873 (The Pile)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.1885. Min Range: -0.1885
Max Act: 0.1607. Min Act: -0.0001
Data Index: 761924 (The Pile)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.1885. Min Range: -0.1885
Max Act: 0.1579. Min Act: -0.0001
Data Index: 246858 (The Pile)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.1885. Min Range: -0.1885
Max Act: 0.1506. Min Act: -0.0001
Data Index: 1165278 (The Pile)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.1885. Min Range: -0.1885
Max Act: 0.1524. Min Act: -0.0001
Data Index: 1463360 (The Pile)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.1885. Min Range: -0.1885
Max Act: 0.1549. Min Act: -0.0001
Data Index: 1743926 (The Pile)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.1885. Min Range: -0.1885
Max Act: 0.1648. Min Act: -0.0001
Data Index: 1840453 (The Pile)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.1885. Min Range: -0.1885
Max Act: 0.1811. Min Act: -0.0001
Data Index: 47577 (The Pile)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.1885. Min Range: -0.1885
Max Act: 0.1535. Min Act: -0.0001
Data Index: 14573 (The Pile)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.1885. Min Range: -0.1885
Max Act: 0.1589. Min Act: -0.0001
Data Index: 1829155 (The Pile)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.1885. Min Range: -0.1885
Max Act: 0.1496. Min Act: -0.0001
Data Index: 1651315 (The Pile)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.1885. Min Range: -0.1885
Max Act: 0.1487. Min Act: -0.0001
Data Index: 21425 (The Pile)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.1885. Min Range: -0.1885
Max Act: 0.1834. Min Act: -0.0001
Data Index: 1288264 (The Pile)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.1885. Min Range: -0.1885
Max Act: 0.1427. Min Act: -0.0001
Data Index: 288864 (The Pile)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.1885. Min Range: -0.1885
Max Act: 0.1801. Min Act: -0.0001
Data Index: 200012 (The Pile)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.1885. Min Range: -0.1885
Max Act: 0.1526. Min Act: -0.0001
Data Index: 718 (The Pile)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #19