Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3621 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 0.0800. Min Range: -0.0800
Max Act: 0.0800. Min Act: -0.0001
Data Index: 1450592 (Python Code)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.0800. Min Range: -0.0800
Max Act: 0.0683. Min Act: -0.0001
Data Index: 539090 (C4 (Web Text))
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.0800. Min Range: -0.0800
Max Act: 0.0628. Min Act: -0.0001
Data Index: 1597262 (Python Code)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.0800. Min Range: -0.0800
Max Act: 0.0612. Min Act: -0.0001
Data Index: 1647903 (Python Code)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.0800. Min Range: -0.0800
Max Act: 0.0622. Min Act: -0.0001
Data Index: 1334438 (C4 (Web Text))
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.0800. Min Range: -0.0800
Max Act: 0.0622. Min Act: -0.0001
Data Index: 1383376 (Python Code)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.0800. Min Range: -0.0800
Max Act: 0.0590. Min Act: -0.0001
Data Index: 1257562 (C4 (Web Text))
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.0800. Min Range: -0.0800
Max Act: 0.0556. Min Act: -0.0001
Data Index: 1548980 (Python Code)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.0800. Min Range: -0.0800
Max Act: 0.0579. Min Act: -0.0001
Data Index: 1226046 (C4 (Web Text))
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.0800. Min Range: -0.0800
Max Act: 0.0575. Min Act: -0.0001
Data Index: 1627787 (Python Code)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.0800. Min Range: -0.0800
Max Act: 0.0584. Min Act: -0.0001
Data Index: 1653806 (Python Code)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.0800. Min Range: -0.0800
Max Act: 0.0560. Min Act: -0.0001
Data Index: 681374 (C4 (Web Text))
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.0800. Min Range: -0.0800
Max Act: 0.0554. Min Act: -0.0001
Data Index: 399446 (C4 (Web Text))
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.0800. Min Range: -0.0800
Max Act: 0.0537. Min Act: -0.0001
Data Index: 1656085 (Python Code)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.0800. Min Range: -0.0800
Max Act: 0.0533. Min Act: -0.0001
Data Index: 1550980 (Python Code)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.0800. Min Range: -0.0800
Max Act: 0.0487. Min Act: -0.0002
Data Index: 1490615 (Python Code)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.0800. Min Range: -0.0800
Max Act: 0.0473. Min Act: -0.0001
Data Index: 451729 (C4 (Web Text))
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.0800. Min Range: -0.0800
Max Act: 0.0511. Min Act: -0.0001
Data Index: 313012 (C4 (Web Text))
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.0800. Min Range: -0.0800
Max Act: 0.0526. Min Act: -0.0001
Data Index: 133995 (C4 (Web Text))
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.0800. Min Range: -0.0800
Max Act: 0.0587. Min Act: -0.0001
Data Index: 1549199 (Python Code)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #19