Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 1861 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 2.8851. Min Range: -2.8851
Max Act: 2.8851. Min Act: -0.0001
Data Index: 1439231 (Python Code)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8851. Min Range: -2.8851
Max Act: 2.4241. Min Act: -0.0001
Data Index: 1654421 (Python Code)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8851. Min Range: -2.8851
Max Act: 2.3436. Min Act: -0.0001
Data Index: 1425083 (Python Code)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8851. Min Range: -2.8851
Max Act: 2.1541. Min Act: -0.0001
Data Index: 1518226 (Python Code)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8851. Min Range: -2.8851
Max Act: 2.0635. Min Act: -0.0001
Data Index: 1374385 (Python Code)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8851. Min Range: -2.8851
Max Act: 1.9984. Min Act: -0.0001
Data Index: 1532580 (Python Code)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8851. Min Range: -2.8851
Max Act: 2.1444. Min Act: -0.0001
Data Index: 1501203 (Python Code)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8851. Min Range: -2.8851
Max Act: 2.0450. Min Act: -0.0001
Data Index: 1600409 (Python Code)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8851. Min Range: -2.8851
Max Act: 2.0428. Min Act: -0.0001
Data Index: 1533757 (Python Code)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8851. Min Range: -2.8851
Max Act: 2.0878. Min Act: -0.0001
Data Index: 1361295 (Python Code)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8851. Min Range: -2.8851
Max Act: 1.8806. Min Act: -0.0001
Data Index: 1546913 (Python Code)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8851. Min Range: -2.8851
Max Act: 1.9917. Min Act: -0.0001
Data Index: 1537434 (Python Code)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8851. Min Range: -2.8851
Max Act: 2.0805. Min Act: -0.0001
Data Index: 1426507 (Python Code)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8851. Min Range: -2.8851
Max Act: 1.9807. Min Act: -0.0001
Data Index: 1568734 (Python Code)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8851. Min Range: -2.8851
Max Act: 1.9769. Min Act: -0.0001
Data Index: 1441377 (Python Code)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8851. Min Range: -2.8851
Max Act: 1.8117. Min Act: -0.0001
Data Index: 1524970 (Python Code)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8851. Min Range: -2.8851
Max Act: 2.0038. Min Act: -0.0001
Data Index: 1373292 (Python Code)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8851. Min Range: -2.8851
Max Act: 1.8820. Min Act: -0.0001
Data Index: 1566334 (Python Code)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8851. Min Range: -2.8851
Max Act: 1.7426. Min Act: -0.0001
Data Index: 1514214 (Python Code)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8851. Min Range: -2.8851
Max Act: 1.7012. Min Act: -0.0001
Data Index: 1643704 (Python Code)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #19