Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2467 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')
Text #0
Max Range: 2.8343. Min Range: -2.8343
Max Act: 2.7490. Min Act: -0.0001
Data Index: 1586641 (Python Code)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8343. Min Range: -2.8343
Max Act: 2.3758. Min Act: -0.0001
Data Index: 1630643 (Python Code)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8343. Min Range: -2.8343
Max Act: 2.6005. Min Act: -0.0001
Data Index: 1539907 (Python Code)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8343. Min Range: -2.8343
Max Act: 2.8343. Min Act: -0.0001
Data Index: 1653317 (Python Code)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8343. Min Range: -2.8343
Max Act: 2.5773. Min Act: -0.0001
Data Index: 1371435 (Python Code)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8343. Min Range: -2.8343
Max Act: 2.4949. Min Act: -0.0001
Data Index: 1534129 (Python Code)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8343. Min Range: -2.8343
Max Act: 2.5132. Min Act: -0.0001
Data Index: 1429326 (Python Code)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8343. Min Range: -2.8343
Max Act: 2.6145. Min Act: -0.0001
Data Index: 1573122 (Python Code)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8343. Min Range: -2.8343
Max Act: 2.6027. Min Act: -0.0001
Data Index: 1621974 (Python Code)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8343. Min Range: -2.8343
Max Act: 2.4635. Min Act: -0.0001
Data Index: 1489947 (Python Code)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8343. Min Range: -2.8343
Max Act: 2.3483. Min Act: -0.0001
Data Index: 1514008 (Python Code)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8343. Min Range: -2.8343
Max Act: 2.5440. Min Act: -0.0001
Data Index: 1610513 (Python Code)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8343. Min Range: -2.8343
Max Act: 2.0646. Min Act: -0.0001
Data Index: 1527881 (Python Code)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8343. Min Range: -2.8343
Max Act: 2.6646. Min Act: -0.0001
Data Index: 1442774 (Python Code)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8343. Min Range: -2.8343
Max Act: 2.4215. Min Act: -0.0001
Data Index: 1629456 (Python Code)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8343. Min Range: -2.8343
Max Act: 2.5264. Min Act: -0.0001
Data Index: 1646941 (Python Code)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8343. Min Range: -2.8343
Max Act: 2.5294. Min Act: -0.0001
Data Index: 1501745 (Python Code)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8343. Min Range: -2.8343
Max Act: 2.3466. Min Act: -0.0001
Data Index: 1518785 (Python Code)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8343. Min Range: -2.8343
Max Act: 2.5016. Min Act: -0.0001
Data Index: 1379432 (Python Code)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8343. Min Range: -2.8343
Max Act: 2.5036. Min Act: -0.0001
Data Index: 1427092 (Python Code)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #19