Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3652 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 0.0731. Min Range: -0.0731
Max Act: 0.0713. Min Act: -0.0001
Data Index: 233480 (C4 (Web Text))
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.0731. Min Range: -0.0731
Max Act: 0.0731. Min Act: -0.0001
Data Index: 603329 (C4 (Web Text))
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.0731. Min Range: -0.0731
Max Act: 0.0672. Min Act: -0.0001
Data Index: 698181 (C4 (Web Text))
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.0731. Min Range: -0.0731
Max Act: 0.0642. Min Act: -0.0001
Data Index: 160649 (C4 (Web Text))
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.0731. Min Range: -0.0731
Max Act: 0.0658. Min Act: -0.0001
Data Index: 1090366 (C4 (Web Text))
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.0731. Min Range: -0.0731
Max Act: 0.0596. Min Act: -0.0001
Data Index: 533683 (C4 (Web Text))
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.0731. Min Range: -0.0731
Max Act: 0.0583. Min Act: -0.0001
Data Index: 1262798 (C4 (Web Text))
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.0731. Min Range: -0.0731
Max Act: 0.0553. Min Act: -0.0001
Data Index: 638535 (C4 (Web Text))
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.0731. Min Range: -0.0731
Max Act: 0.0558. Min Act: -0.0001
Data Index: 252406 (C4 (Web Text))
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.0731. Min Range: -0.0731
Max Act: 0.0518. Min Act: -0.0001
Data Index: 1618429 (Python Code)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.0731. Min Range: -0.0731
Max Act: 0.0564. Min Act: -0.0001
Data Index: 644839 (C4 (Web Text))
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.0731. Min Range: -0.0731
Max Act: 0.0546. Min Act: -0.0001
Data Index: 182688 (C4 (Web Text))
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.0731. Min Range: -0.0731
Max Act: 0.0512. Min Act: -0.0001
Data Index: 1363816 (Python Code)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.0731. Min Range: -0.0731
Max Act: 0.0665. Min Act: -0.0001
Data Index: 1371544 (Python Code)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.0731. Min Range: -0.0731
Max Act: 0.0547. Min Act: -0.0001
Data Index: 1272055 (C4 (Web Text))
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.0731. Min Range: -0.0731
Max Act: 0.0526. Min Act: -0.0001
Data Index: 1648482 (Python Code)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.0731. Min Range: -0.0731
Max Act: 0.0572. Min Act: -0.0001
Data Index: 311402 (C4 (Web Text))
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.0731. Min Range: -0.0731
Max Act: 0.0551. Min Act: -0.0001
Data Index: 391532 (C4 (Web Text))
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.0731. Min Range: -0.0731
Max Act: 0.0577. Min Act: -0.0001
Data Index: 1278546 (C4 (Web Text))
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.0731. Min Range: -0.0731
Max Act: 0.0582. Min Act: -0.0001
Data Index: 1551551 (Python Code)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #19